© 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 Local
    9. 6-RES_SCL-AJT
    11. 33506
    Prev
    Next
    INDEX
    Explanations

    character strings with varying accents and special characters

    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
    216
    +0.14
    0.7%
    130
    +0.11
    0.6%
    284
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.10
    326
    +0.11
    0.19
    123
    +0.10
    0.07
    Negative Logits
    ukong
    -0.67
    etsk
    -0.67
    ministic
    -0.65
    raints
    -0.61
     protector
    -0.61
    inators
    -0.60
    lessly
    -0.58
    aciously
    -0.57
    inois
    -0.56
    idges
    -0.56
    POSITIVE LOGITS
    ¡
    0.96
    ¥
    0.93
    ´
    0.91
    Į
    0.86
    ©
    0.86
    ģ
    0.85
    ļ
    0.84
    ¼
    0.84
    µ
    0.83
    ÙĬ
    0.83
    Activations Density 6.592%

    No Known Activations