© 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 Local
    9. 6-RES_SCL-AJT
    11. 35547
    Prev
    Next
    INDEX
    Explanations

    words related to dolls

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.12
    0.9%
    383
    +0.08
    0.6%
    99
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.12
    0.10
    383
    +0.08
    0.09
    288
    +0.08
    0.17
    Negative Logits
    ################
    -0.52
    ãĥ¥
    -0.52
    GGGGGGGG
    -0.51
    TAIN
    -0.47
    EED
    -0.45
    NING
    -0.44
    riott
    -0.43
    ELY
    -0.43
    RAW
    -0.42
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.42
    POSITIVE LOGITS
     dolls
    0.62
    maker
    0.61
     doll
    0.61
    ies
    0.53
    hops
    0.53
    ophone
    0.53
    wright
    0.51
    oru
    0.50
    makers
    0.49
    okia
    0.49
    Activations Density 5.288%

    No Known Activations