© 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 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. 392
    Prev
    Next
    INDEX
    Explanations

    references to dolls

    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
    99
    +0.14
    0.7%
    288
    +0.13
    0.6%
    286
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.09
    288
    +0.13
    0.11
    99
    +0.12
    0.07
    Negative Logits
    rament
    -0.74
    ################
    -0.74
    ãĥ¥
    -0.74
    TAIN
    -0.71
    GGGGGGGG
    -0.71
    ELY
    -0.71
    utherford
    -0.69
    RAW
    -0.69
     TRANS
    -0.69
    acular
    -0.68
    POSITIVE LOGITS
    maker
    0.93
     doll
    0.90
     dolls
    0.89
    hops
    0.84
    imates
    0.82
    ongs
    0.77
    oru
    0.76
     Doll
    0.75
    wright
    0.75
    ophone
    0.73
    Activations Density 1.108%

    No Known Activations