© 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. 11669
    Prev
    Next
    INDEX
    Explanations

    references to locations, activities and attributes in a script or story

    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
    3
    +0.05
    0.5%
    702
    +0.05
    0.5%
    639
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.05
    0.05
    160
    +0.05
    0.04
    442
    +0.04
    0.03
    Negative Logits
     UNIVERS
    -0.43
    çīĪ
    -0.36
    ;;;;;;;;;;;;
    -0.36
     Noir
    -0.35
     501
    -0.34
     DARK
    -0.33
    pedia
    -0.33
     \\
    -0.32
     Dusk
    -0.31
    REDACTED
    -0.31
    POSITIVE LOGITS
    ior
    0.34
    rative
    0.33
    iness
    0.32
    rol
    0.32
    graded
    0.31
    orer
    0.31
     weeds
    0.31
    ested
    0.31
    ifled
    0.31
    arettes
    0.31
    Activations Density 0.104%

    No Known Activations