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

    Neuronpedia

    APICircuit 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. 45628
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications or instructions

    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
    7
    +0.08
    0.5%
    466
    +0.07
    0.4%
    706
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.08
    0.27
    373
    +0.07
    -0.25
    6
    +0.07
    0.14
    Negative Logits
    schild
    -0.56
    ailability
    -0.51
    EMS
    -0.51
    ģ«
    -0.48
     Frames
    -0.47
     Components
    -0.45
    usercontent
    -0.43
    ERG
    -0.42
    EMP
    -0.42
    ¥µ
    -0.41
    POSITIVE LOGITS
     Nieto
    0.73
    rence
    0.59
    thood
    0.53
    ration
    0.52
    asus
    0.52
    chio
    0.51
    utor
    0.50
    ciating
    0.50
    rency
    0.50
    cially
    0.49
    Activations Density 13.654%

    No Known Activations