© 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. 12892
    Prev
    Next
    INDEX
    Explanations

    references to bills or legislation in political contexts

    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
    566
    +0.12
    0.6%
    377
    +0.12
    0.6%
    13
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.12
    0.08
    326
    +0.12
    0.14
    659
    +0.12
    0.08
    Negative Logits
    igators
    -0.79
     Eag
    -0.75
    omore
    -0.75
    geons
    -0.74
    nces
    -0.73
    ographers
    -0.73
    perse
    -0.73
    ciating
    -0.71
    opol
    -0.70
    mopolitan
    -0.70
    POSITIVE LOGITS
    RIC
    1.24
    BI
    1.05
    FL
    1.04
    RA
    1.02
    SPA
    1.01
    STR
    0.99
    RAM
    0.96
    HA
    0.94
    ONY
    0.94
    USE
    0.93
    Activations Density 3.471%

    No Known Activations