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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3185
    Prev
    Next
    INDEX
    Explanations

    specific examples within texts

    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
    730
    +0.13
    0.4%
    236
    +0.12
    0.4%
    514
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    514
    +0.13
    0.04
    70
    +0.12
    0.06
    236
    +0.12
    0.06
    Negative Logits
    obyl
    -0.96
    PF
    -0.87
    theless
    -0.86
    ULTS
    -0.82
    culosis
    -0.79
     CY
    -0.78
     Printing
    -0.77
    omore
    -0.77
    usal
    -0.74
    icative
    -0.73
    POSITIVE LOGITS
     Stamp
    0.85
     persu
    0.79
     mortg
    0.78
     challeng
    0.76
     Katz
    0.75
    á¸
    0.73
     insist
    0.73
     rehe
    0.73
     forgive
    0.72
     Fein
    0.71
    Activations Density 1.130%

    No Known Activations