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. 4092
    Prev
    Next
    INDEX
    Explanations

    intriguing biographical information about individuals

    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
    •Layer 6 UMAP region: e2e-recon outlier bottom right - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    640
    +0.19
    1.1%
    447
    +0.17
    1.0%
    745
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.19
    0.35
    160
    +0.17
    0.28
    442
    +0.13
    0.22
    Negative Logits
     overlook
    -0.56
     swall
    -0.54
     cum
    -0.53
    jah
    -0.52
     possible
    -0.51
     semen
    -0.51
    borough
    -0.51
     disapp
    -0.51
     mang
    -0.50
     Franc
    -0.50
    POSITIVE LOGITS
    Contents
    0.83
    advertisement
    0.68
    Sold
    0.63
    SCP
    0.63
    Weight
    0.62
    unks
    0.60
    Nut
    0.59
    redients
    0.59
    Opt
    0.59
    ourge
    0.59
    Activations Density 2.935%

    No Known Activations