© 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. 13835
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and governmental matters

    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
    +0.39
    2.3%
    393
    +0.25
    1.5%
    640
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.39
    0.42
    447
    +0.25
    0.45
    64
    +0.13
    -0.22
    Negative Logits
    ceive
    -0.64
    thood
    -0.64
    ÏĢ
    -0.63
    antes
    -0.60
    å·
    -0.60
    cial
    -0.59
    assed
    -0.58
    leen
    -0.57
    200000
    -0.57
    ustom
    -0.55
    POSITIVE LOGITS
    resa
    1.05
     latter
    1.02
     latest
    1.00
    oret
    0.99
    odore
    0.98
     biggest
    0.82
     remainder
    0.82
     earliest
    0.80
     vast
    0.79
     aforementioned
    0.77
    Activations Density 15.775%

    No Known Activations