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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45768
    Prev
    Next
    INDEX
    Explanations

    positive phrases or expressions

    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
    610
    +0.09
    0.5%
    559
    +0.09
    0.5%
    459
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.09
    0.27
    608
    +0.09
    0.19
    526
    +0.09
    -0.06
    Negative Logits
    olicy
    -0.66
    cum
    -0.62
    ural
    -0.59
    aults
    -0.57
    atum
    -0.56
    soDeliveryDate
    -0.55
    umed
    -0.54
     Tsukuyomi
    -0.53
    mage
    -0.53
    é¾
    -0.52
    POSITIVE LOGITS
    bye
    0.72
     tid
    0.63
     congr
    0.62
    noon
    0.57
     remind
    0.56
     reassure
    0.55
     ðŁĻĤ
    0.54
     ya
    0.54
    elight
    0.54
     Torrent
    0.54
    Activations Density 10.397%

    No Known Activations