© 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. 1315
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where a contrasting idea or point of view is presented

    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
    679
    +0.16
    0.6%
    572
    +0.16
    0.6%
    450
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    572
    +0.16
    0.07
    450
    +0.16
    0.07
    221
    +0.14
    0.05
    Negative Logits
    esses
    -0.85
     Goth
    -0.78
     sights
    -0.78
     woods
    -0.75
    ducers
    -0.74
    letter
    -0.74
    ainment
    -0.74
     backyard
    -0.74
    IQ
    -0.73
     roller
    -0.73
    POSITIVE LOGITS
    tons
    1.16
    lers
    1.00
    chery
    0.94
    chart
    0.91
    ler
    0.91
     interestingly
    0.91
     importantly
    0.91
    chers
    0.90
    herty
    0.88
     Err
    0.88
    Activations Density 0.643%

    No Known Activations