© 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. 1262
    Prev
    Next
    INDEX
    Explanations

    specific place names, especially those related to astronomical observatories

    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
    284
    +0.13
    0.6%
    497
    +0.12
    0.6%
    249
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.07
    659
    +0.12
    0.06
    232
    +0.09
    0.05
    Negative Logits
    Ö¼
    -0.70
     allowances
    -0.67
    OTOS
    -0.64
    }}}
    -0.55
     distinctions
    -0.55
     Typh
    -0.54
    :{
    -0.54
    recomm
    -0.53
     glim
    -0.53
    Notice
    -0.53
    POSITIVE LOGITS
    ocene
    0.87
    nick
    0.85
    encia
    0.83
    ieri
    0.82
    dale
    0.82
    agne
    0.77
    ophone
    0.77
    oche
    0.74
    iere
    0.74
    nant
    0.73
    Activations Density 0.860%

    No Known Activations