© 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. 11208
    Prev
    Next
    INDEX
    Explanations

    names and rare medical terms

    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
    286
    +0.14
    0.5%
    392
    +0.14
    0.5%
    146
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.10
    288
    +0.14
    0.12
    11
    +0.14
    0.05
    Negative Logits
    NetMessage
    -1.02
    venants
    -0.89
    engers
    -0.89
    zees
    -0.87
     cutter
    -0.86
     Scotia
    -0.85
    pper
    -0.85
    ttes
    -0.84
    PDATE
    -0.84
    cffff
    -0.84
    POSITIVE LOGITS
    ento
    1.26
    matical
    1.22
    ents
    1.20
    gdala
    1.20
    entary
    1.19
    s
    1.15
    mable
    1.15
    encer
    1.12
    acy
    1.11
    atsu
    1.10
    Activations Density 1.381%

    No Known Activations