© 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. 13894
    Prev
    Next
    INDEX
    Explanations

    phrases related to a negative medical condition or state of health

    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
    178
    +0.14
    0.6%
    285
    +0.10
    0.5%
    655
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.14
    0.11
    278
    +0.10
    0.05
    616
    +0.10
    0.05
    Negative Logits
    ļéĨĴ
    -0.81
    */(
    -0.80
    EStream
    -0.78
    uyomi
    -0.75
    EStreamFrame
    -0.74
    £ı
    -0.73
    ©¶æ¥µ
    -0.71
     compr
    -0.71
     Citation
    -0.66
    theless
    -0.66
    POSITIVE LOGITS
    uminati
    1.45
    ogical
    1.21
    inois
    1.21
    umin
    1.20
    awar
    1.17
    iberal
    1.16
    icit
    1.07
    usive
    1.04
    iquid
    1.03
    igan
    1.00
    Activations Density 4.403%

    No Known Activations