Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 3980
    Prev
    Next
    INDEX
    Explanations

    ethnic and religious references, particularly in relation to different groups, minorities, and communities

    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
    288
    +0.23
    1.0%
    447
    +0.21
    0.9%
    289
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.23
    0.10
    57
    +0.21
    0.07
    220
    +0.12
    0.08
    Negative Logits
    uden
    -0.91
    agher
    -0.88
    tower
    -0.87
    aday
    -0.87
    aunder
    -0.86
    etheus
    -0.80
    OHN
    -0.77
    =-=-=-=-
    -0.76
    uckland
    -0.75
    backs
    -0.75
    POSITIVE LOGITS
     cleansing
    1.25
    ities
    1.05
     minorities
    1.04
     minority
    0.88
     groups
    0.84
     appropriation
    0.82
     supremacists
    0.81
     communities
    0.81
     identity
    0.81
     affiliation
    0.81
    Activations Density 7.056%

    No Known Activations