© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13884
    Prev
    Next
    INDEX
    Explanations

    gender-related terms, focusing on males, such as male, females, mating, genders, and reproductive acts

    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
    99
    +0.19
    0.7%
    447
    +0.14
    0.5%
    48
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.19
    0.13
    711
    +0.14
    0.05
    38
    +0.13
    0.09
    Negative Logits
    krit
    -1.20
    heet
    -1.12
    rieg
    -1.00
    hemy
    -1.00
    bley
    -0.96
    ovie
    -0.93
    anwhile
    -0.93
    aido
    -0.92
    uden
    -0.91
    weet
    -0.91
    POSITIVE LOGITS
    volent
    1.90
     genital
    1.26
    vol
    1.11
     circumcision
    1.00
     infertility
    0.97
     reproductive
    0.97
     anatomy
    0.94
     genitals
    0.92
     supremacy
    0.89
     offspring
    0.89
    Activations Density 10.086%

    No Known Activations