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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45101
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms and indicators

    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
    +0.33
    1.7%
    497
    +0.16
    0.8%
    35
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.33
    0.22
    35
    +0.16
    0.12
    173
    +0.09
    0.11
    Negative Logits
    anyl
    -0.55
    ¥ŀ
    -0.55
    raviolet
    -0.54
    laim
    -0.54
    arton
    -0.54
    edient
    -0.54
    leys
    -0.54
    berra
    -0.53
    edi
    -0.53
    iden
    -0.53
    POSITIVE LOGITS
     apiece
    0.82
    0000000000000000
    0.72
    %,
    0.72
    %.
    0.70
    %;
    0.69
     per
    0.69
    0000000
    0.67
     crore
    0.65
    00
    0.65
    Mbps
    0.64
    Activations Density 22.171%

    No Known Activations