© 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. 45907
    Prev
    Next
    INDEX
    Explanations

    smooth and creamy textures or substances

    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
    481
    +0.12
    0.8%
    373
    +0.09
    0.6%
    497
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.10
    406
    +0.09
    0.08
    678
    +0.09
    0.07
    Negative Logits
     Corker
    -0.55
     Bureau
    -0.48
    ublic
    -0.47
    cha
    -0.47
     Geral
    -0.46
    uses
    -0.45
     Solitaire
    -0.45
     Chau
    -0.45
    ajo
    -0.45
    yden
    -0.44
    POSITIVE LOGITS
    hearted
    0.56
     seas
    0.53
    monds
    0.52
     outp
    0.51
     metallic
    0.50
     retri
    0.50
     depths
    0.50
    eyed
    0.50
     cloudy
    0.50
     clouds
    0.48
    Activations Density 4.230%

    No Known Activations