© 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. 4135
    Prev
    Next
    INDEX
    Explanations

    mentions of political leaders and government-related terms

    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
    +0.20
    0.9%
    224
    +0.13
    0.5%
    679
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.20
    0.14
    657
    +0.13
    0.14
    146
    +0.13
    0.11
    Negative Logits
    INGTON
    -0.87
     Seah
    -0.78
    Operation
    -0.74
    TPS
    -0.71
    Population
    -0.70
    Grab
    -0.69
    LAN
    -0.68
    aband
    -0.68
    ITNESS
    -0.67
     Boy
    -0.66
    POSITIVE LOGITS
    hips
    1.64
    hip
    1.55
    paces
    1.22
    ervatives
    1.16
    mith
    1.11
    ettings
    1.02
    pring
    0.96
    '
    0.95
    pace
    0.95
    ervative
    0.91
    Activations Density 10.303%

    No Known Activations