© 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. 4735
    Prev
    Next
    INDEX
    Explanations

    instances of words related to political conflict, international relations, and social issues

    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
    +0.25
    1.3%
    460
    +0.10
    0.5%
    319
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.25
    0.08
    114
    +0.10
    0.07
    455
    +0.09
    0.12
    Negative Logits
    ongyang
    -0.71
    roe
    -0.60
    opoly
    -0.59
    oir
    -0.57
    hesive
    -0.57
    gey
    -0.56
    kefeller
    -0.56
    ocide
    -0.55
    scribe
    -0.55
    redit
    -0.55
    POSITIVE LOGITS
     involving
    0.85
    cases
    0.69
    cale
    0.68
    hooting
    0.67
    rooms
    0.66
    hots
    0.65
     cases
    0.65
    hops
    0.64
    finder
    0.64
    manship
    0.63
    Activations Density 7.275%

    No Known Activations