© 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. 35557
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal hygiene and health information

    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
    +0.16
    0.7%
    670
    +0.11
    0.5%
    598
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.16
    0.42
    447
    +0.11
    0.44
    64
    +0.10
    -0.18
    Negative Logits
    etheless
    -0.99
    icals
    -0.87
    aird
    -0.82
    oran
    -0.81
    ascal
    -0.78
    padding
    -0.76
    ajo
    -0.75
    dies
    -0.74
    anguage
    -0.74
    axter
    -0.73
    POSITIVE LOGITS
    ppe
    1.03
    olate
    0.93
     versa
    0.88
    ño
    0.84
    lda
    0.82
    gow
    0.79
    e
    0.77
     Amend
    0.73
    ller
    0.71
    yi
    0.71
    Activations Density 9.550%

    No Known Activations