© 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. 1821
    Prev
    Next
    INDEX
    Explanations

    phrases related to obstacles or challenges

    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
    160
    +0.14
    0.5%
    412
    +0.12
    0.4%
    46
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.14
    0.04
    512
    +0.12
    0.03
    435
    +0.11
    0.02
    Negative Logits
    incinn
    -1.12
    milo
    -1.09
    acca
    -1.04
    resent
    -1.00
    ¥µ
    -0.96
    oute
    -0.96
    iture
    -0.96
    iosyncr
    -0.92
     Flavoring
    -0.90
    inately
    -0.88
    POSITIVE LOGITS
    ward
    1.24
    WARD
    1.11
    finding
    0.99
    finder
    0.88
     thereof
    0.81
    lay
    0.78
    lands
    0.78
    liness
    0.78
    crew
    0.77
     thereto
    0.76
    Activations Density 0.362%

    No Known Activations