Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13288
    Prev
    Next
    INDEX
    Explanations

    names or mentions of the name "Andy"

    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
    +0.15
    0.7%
    566
    +0.11
    0.5%
    636
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.17
    326
    +0.11
    0.16
    502
    +0.10
    0.05
    Negative Logits
    hips
    -0.90
    ingen
    -0.79
    inals
    -0.77
    nces
    -0.74
    maid
    -0.74
    olid
    -0.68
    naire
    -0.68
    ngth
    -0.67
    porting
    -0.67
    iotic
    -0.66
    POSITIVE LOGITS
    visors
    0.73
     Dalton
    0.72
     Weir
    0.71
     Neil
    0.69
     Coul
    0.69
     Cohen
    0.68
     Neal
    0.66
     Andy
    0.66
     Grove
    0.65
     Kaufman
    0.64
    Activations Density 4.597%

    No Known Activations