© 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. 13756
    Prev
    Next
    INDEX
    Explanations

    mentions of social and political issues or controversies

    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
    36
    +0.11
    0.5%
    326
    +0.11
    0.5%
    152
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    696
    +0.11
    0.13
    536
    +0.11
    0.11
    767
    +0.10
    0.12
    Negative Logits
     Lauder
    -0.94
     Reef
    -0.91
     Leilan
    -0.89
    EStream
    -0.71
     Seah
    -0.70
     misunder
    -0.70
    BuyableInstoreAndOnline
    -0.70
     constitu
    -0.69
    è¦ļéĨĴ
    -0.67
    ij士
    -0.67
    POSITIVE LOGITS
    anc
    0.96
    ust
    0.93
    aj
    0.90
    aper
    0.88
    ind
    0.87
    odd
    0.87
    adi
    0.85
    rew
    0.81
    alf
    0.81
    ans
    0.81
    Activations Density 1.415%

    No Known Activations