© 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. 39603
    Prev
    Next
    INDEX
    Explanations

    references to criminal activities or scandals involving individuals

    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
    +0.14
    1.1%
    393
    +0.06
    0.5%
    39
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.14
    0.22
    138
    +0.06
    0.18
    167
    +0.06
    -0.04
    Negative Logits
    ledge
    -0.42
     wisely
    -0.39
    gue
    -0.39
    ãĥ¯
    -0.37
    iencies
    -0.36
    ieties
    -0.36
    hap
    -0.35
    bridge
    -0.34
    auntlet
    -0.34
    tackle
    -0.34
    POSITIVE LOGITS
     impending
    0.44
     upcoming
    0.40
     sightings
    0.38
     purported
    0.37
     missing
    0.36
     cats
    0.34
     whereabouts
    0.34
     furry
    0.33
     contents
    0.33
    ideos
    0.33
    Activations Density 15.571%

    No Known Activations