© 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. 13058
    Prev
    Next
    INDEX
    Explanations

    specific references to dates, events, and individuals related to politics

    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
    +0.30
    1.5%
    393
    +0.15
    0.7%
    526
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.30
    0.16
    22
    +0.15
    0.18
    29
    +0.11
    0.19
    Negative Logits
    tar
    -0.68
     lodged
    -0.67
    CLASSIFIED
    -0.64
    llor
    -0.60
    caster
    -0.60
     incumb
    -0.60
    username
    -0.59
    linger
    -0.59
    76561
    -0.59
    killed
    -0.57
    POSITIVE LOGITS
     spite
    1.23
     regards
    1.22
     lieu
    1.20
     accordance
    1.16
     terms
    1.11
     relation
    1.09
     vain
    1.09
     vitro
    1.08
    clus
    1.05
     situ
    1.04
    Activations Density 10.020%

    No Known Activations