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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 4966
    Prev
    Next
    INDEX
    Explanations

    dialogue interactions and exchange of information between characters in a story

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    273
    +0.12
    0.4%
    224
    +0.12
    0.4%
    393
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    473
    +0.12
    0.07
    598
    +0.12
    0.07
    393
    +0.12
    0.19
    Negative Logits
    ansk
    -0.96
    aeda
    -0.93
    rongh
    -0.92
    anchester
    -0.86
    interstitial
    -0.83
    izons
    -0.82
    agonists
    -0.82
    inventoryQuantity
    -0.82
    igmatic
    -0.79
    ymm
    -0.78
    POSITIVE LOGITS
     subsequently
    1.46
     promptly
    1.45
     complied
    1.41
     replied
    1.27
     responded
    1.26
    gered
    1.23
     duly
    1.22
     proceeded
    1.18
     succeeded
    1.17
     then
    1.15
    Activations Density 5.380%

    No Known Activations