© 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. 11007
    Prev
    Next
    INDEX
    Explanations

    similarities or resemblances between different entities

    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
    1
    +0.15
    0.6%
    504
    +0.12
    0.5%
    99
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.15
    0.07
    438
    +0.12
    0.05
    99
    +0.12
    0.05
    Negative Logits
    akings
    -0.79
    adh
    -0.70
    die
    -0.68
    Fe
    -0.68
    starter
    -0.67
    Ott
    -0.67
     Nou
    -0.67
    erenn
    -0.65
    Published
    -0.65
     Nights
    -0.65
    POSITIVE LOGITS
    lihood
    1.55
    ively
    1.02
     likeness
    0.91
     twins
    0.90
    liness
    0.83
    emort
    0.81
    icut
    0.80
    ingly
    0.79
    minded
    0.78
    etically
    0.77
    Activations Density 1.031%

    No Known Activations