© 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. 34025
    Prev
    Next
    INDEX
    Explanations

    names, specifically the variety that includes both common first names and surnames

    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
    224
    +0.13
    0.6%
    447
    +0.13
    0.6%
    326
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.20
    288
    +0.13
    0.19
    659
    +0.12
    0.10
    Negative Logits
    arist
    -0.71
     Lakes
    -0.70
     Jagu
    -0.66
     advers
    -0.63
    LOAD
    -0.63
    PF
    -0.60
    yah
    -0.59
     burdens
    -0.58
     Manz
    -0.58
     disadvant
    -0.58
    POSITIVE LOGITS
     Tracy
    0.88
     Spencer
    0.82
    cil
    0.79
    rette
    0.78
    ulators
    0.78
    ENCE
    0.77
     Ack
    0.75
    olson
    0.75
    ulations
    0.74
    ylon
    0.74
    Activations Density 6.365%

    No Known Activations