© 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. 5449
    Prev
    Next
    INDEX
    Explanations

    topics of conversation

    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
    393
    +0.27
    1.0%
    235
    +0.16
    0.6%
    155
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.27
    0.07
    723
    +0.16
    0.04
    405
    +0.13
    0.05
    Negative Logits
    strap
    -0.94
    OGR
    -0.81
    hold
    -0.81
    serv
    -0.78
    held
    -0.78
     Detected
    -0.78
    hai
    -0.77
    ©¶æ¥µ
    -0.76
    HT
    -0.75
    iaries
    -0.74
    POSITIVE LOGITS
     reforming
    1.00
     topics
    0.97
     how
    0.92
     quitting
    0.89
     improving
    0.88
     whether
    0.86
     internally
    0.86
     halfway
    0.86
     these
    0.85
     repealing
    0.84
    Activations Density 0.505%

    No Known Activations