© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6775
    Prev
    Next
    INDEX
    Explanations

    mentions of members or groups within a community or organization in various contexts

    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
    679
    +0.31
    1.0%
    116
    +0.15
    0.5%
    386
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.31
    0.06
    386
    +0.15
    0.05
    146
    +0.15
    0.04
    Negative Logits
    trop
    -1.05
    enegger
    -1.00
    ILLE
    -1.00
    anche
    -0.98
     Tropical
    -0.95
    BUS
    -0.95
    BAT
    -0.92
    uras
    -0.89
    ython
    -0.88
    orse
    -0.87
    POSITIVE LOGITS
    hips
    2.13
    doms
    1.51
    member
    1.41
    hip
    1.35
     dues
    1.26
    holders
    1.25
    ials
    1.25
    members
    1.24
    holder
    1.21
    cius
    1.17
    Activations Density 0.558%

    No Known Activations