© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 Local
    9. 6-RES_SCL-AJT
    11. 35158
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names (both first and last names) of individuals

    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
    +0.14
    0.7%
    430
    +0.10
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.14
    0.19
    653
    +0.10
    0.08
    68
    +0.10
    0.03
    Negative Logits
    unct
    -0.77
    ORD
    -0.74
    wrapper
    -0.68
    iculty
    -0.64
    hovah
    -0.63
    eering
    -0.63
    internet
    -0.60
    ebus
    -0.60
     warped
    -0.58
    oler
    -0.58
    POSITIVE LOGITS
    icide
    0.88
    atan
    0.87
    gha
    0.83
    seless
    0.74
    jit
    0.73
     Rice
    0.73
    hiro
    0.72
    icides
    0.72
    zanne
    0.71
    vation
    0.70
    Activations Density 12.482%

    No Known Activations