© 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. 3936
    Prev
    Next
    INDEX
    Explanations

    words related to politics and specific technical terms

    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
    137
    +0.06
    0.4%
    564
    +0.06
    0.4%
    525
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.06
    0.19
    444
    +0.06
    0.05
    160
    +0.06
    0.14
    Negative Logits
    Newsletter
    -0.46
    SOURCE
    -0.45
    KO
    -0.44
     EDITION
    -0.43
    Ö¼
    -0.42
     HIT
    -0.42
    mble
    -0.41
    ãĥ¼ãĥĨãĤ£
    -0.41
    olicy
    -0.40
    isSpecialOrderable
    -0.40
    POSITIVE LOGITS
    istic
    0.68
    ista
    0.59
    pha
    0.59
    ogue
    0.59
    axy
    0.58
    endar
    0.53
    adin
    0.53
    ibr
    0.53
    icious
    0.52
    ogical
    0.52
    Activations Density 6.903%

    No Known Activations