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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7662
    Prev
    Next
    INDEX
    Explanations

    numbers or measurements

    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
    647
    +0.11
    0.5%
    444
    +0.10
    0.5%
    284
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.06
    373
    +0.10
    -0.02
    626
    +0.10
    0.04
    Negative Logits
     STATS
    -0.66
    WARE
    -0.65
     reflection
    -0.63
    CLOSE
    -0.61
    Reviewer
    -0.61
     VIDE
    -0.61
    duino
    -0.59
     playback
    -0.59
     witnessing
    -0.58
     loud
    -0.58
    POSITIVE LOGITS
    ado
    0.89
    edo
    0.86
    alle
    0.80
    urch
    0.80
    ago
    0.77
    asury
    0.77
    ias
    0.76
    ouse
    0.76
    orrow
    0.75
    ons
    0.75
    Activations Density 0.413%

    No Known Activations