© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5828
    Prev
    Next
    INDEX
    Explanations

    references to terms related to government, politics, and legal matters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    311
    +0.13
    0.6%
    288
    +0.12
    0.5%
    159
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.05
    311
    +0.12
    0.01
    232
    +0.11
    0.03
    Negative Logits
    è¦ļéĨĴ
    -0.89
    ãĥ£
    -0.84
     Forsaken
    -0.73
    lihood
    -0.73
    lifting
    -0.72
     Warcraft
    -0.72
    aukee
    -0.70
     Aly
    -0.68
    ICAN
    -0.67
    lift
    -0.66
    POSITIVE LOGITS
    rets
    1.24
    recy
    1.19
    urities
    1.17
    ular
    1.14
    ularity
    1.05
    aucus
    1.03
    ured
    1.02
    unia
    1.01
    ession
    0.99
    utes
    0.97
    Activations Density 0.438%

    No Known Activations