© 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. 13148
    Prev
    Next
    INDEX
    Explanations

    references to societal issues or contentious topics, particularly related to justice, politics, and community

    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
    +0.24
    1.0%
    129
    +0.11
    0.5%
    491
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.24
    0.14
    314
    +0.11
    -0.07
    701
    +0.10
    0.09
    Negative Logits
     nomine
    -0.73
    mson
    -0.73
    intendent
    -0.66
     [*]
    -0.66
     disadvant
    -0.66
    umably
    -0.66
    umerous
    -0.65
    factor
    -0.64
    mington
    -0.64
     terminating
    -0.64
    POSITIVE LOGITS
     Loud
    0.93
     Crus
    0.86
     Strategies
    0.83
     Ruin
    0.83
     Pupp
    0.82
    Haunted
    0.81
     Heroes
    0.78
     Legacy
    0.78
     Projects
    0.78
     Cowboy
    0.77
    Activations Density 16.378%

    No Known Activations