© 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. 34948
    Prev
    Next
    INDEX
    Explanations

    sections containing character dialogues within quotation marks

    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
    +0.25
    1.1%
    393
    +0.14
    0.6%
    640
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.25
    0.32
    255
    +0.14
    0.14
    160
    +0.13
    0.20
    Negative Logits
     overlook
    -0.75
     scheduled
    -0.72
     moder
    -0.71
     favor
    -0.71
     termin
    -0.71
     disappro
    -0.71
     overhaul
    -0.71
     lookout
    -0.71
     inflic
    -0.69
     slate
    -0.69
    POSITIVE LOGITS
    They
    1.29
    We
    1.28
    Our
    1.22
    Sometimes
    1.21
    It
    1.19
    There
    1.18
    Where
    1.16
    I
    1.15
    Because
    1.14
    Anything
    1.14
    Activations Density 9.763%

    No Known Activations