© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13766
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and justice

    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
    +0.18
    0.8%
    583
    +0.12
    0.5%
    125
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.18
    0.14
    679
    +0.12
    0.23
    640
    +0.11
    0.25
    Negative Logits
    nen
    -0.73
    ãĤ¨ãĥ«
    -0.66
    Äĩ
    -0.63
    ãĥ£
    -0.63
    oola
    -0.61
    sterdam
    -0.61
    æĹ
    -0.61
    pload
    -0.60
     Forsaken
    -0.59
    ved
    -0.59
    POSITIVE LOGITS
    ombat
    0.76
    deals
    0.67
    icators
    0.67
    heit
    0.65
    ieties
    0.65
     gestures
    0.64
    ivals
    0.64
    achine
    0.64
    agogue
    0.61
    ainer
    0.61
    Activations Density 12.192%

    No Known Activations