© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13647
    Prev
    Next
    INDEX
    Explanations

    discussions or considerations about the potential drawbacks or implications of certain actions or decisions

    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
    676
    +0.15
    0.5%
    482
    +0.13
    0.5%
    760
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.15
    0.04
    461
    +0.13
    0.04
    336
    +0.13
    0.03
    Negative Logits
     medium
    -1.00
    iles
    -0.91
    machine
    -0.89
    ternity
    -0.87
    ylon
    -0.81
    actionDate
    -0.81
    nesota
    -0.76
     model
    -0.76
     lure
    -0.76
    expensive
    -0.75
    POSITIVE LOGITS
    âĢ
    1.45
     âĢ
    1.27
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    1.20
    âĢ²
    1.18
    ÃĥÃĤ
    1.17
     ÂŃ
    1.11
    ÂŃ
    1.09
    **
    1.09
    –
    1.06
    âĢł
    1.05
    Activations Density 0.853%

    No Known Activations