© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40690
    Prev
    Next
    INDEX
    Explanations

    phrases related to government oversight and political controversies

    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
    +0.16
    0.8%
    393
    +0.15
    0.7%
    690
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.16
    0.32
    362
    +0.15
    0.21
    385
    +0.09
    0.22
    Negative Logits
    obyl
    -0.70
    ashtra
    -0.68
    ptoms
    -0.66
    icious
    -0.63
    anguage
    -0.63
    igue
    -0.61
    igible
    -0.59
    bia
    -0.58
    vana
    -0.57
    BuyableInstoreAndOnline
    -0.57
    POSITIVE LOGITS
     extracting
    0.70
     course
    0.69
     Nanto
    0.66
     manipulating
    0.63
     sorts
    0.56
     sorcery
    0.55
    DOM
    0.55
     ART
    0.55
     transl
    0.54
     executing
    0.53
    Activations Density 11.265%

    No Known Activations