© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35114
    Prev
    Next
    INDEX
    Explanations

    information about legal and political issues, especially related to public statements and statements from authorities, such as public figures and government representatives

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.21
    1.0%
    157
    +0.10
    0.5%
    609
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.21
    0.33
    679
    +0.10
    0.26
    255
    +0.10
    0.13
    Negative Logits
    inally
    -0.70
    Pacific
    -0.70
     Yamato
    -0.69
     Surge
    -0.69
    Ö¼
    -0.65
    lectic
    -0.64
    ulhu
    -0.61
    ãĥīãĥ©ãĤ´ãĥ³
    -0.61
    akuya
    -0.60
    idious
    -0.60
    POSITIVE LOGITS
     opinion
    0.73
     ORDER
    0.70
    atures
    0.69
    houses
    0.65
    ourse
    0.63
    pection
    0.62
     bond
    0.62
    rait
    0.59
     sworn
    0.59
     refere
    0.58
    Activations Density 17.608%

    No Known Activations