© 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. 33767
    Prev
    Next
    INDEX
    Explanations

    social media usernames and handles

    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
    640
    +0.12
    0.5%
    314
    +0.12
    0.5%
    385
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.12
    0.20
    362
    +0.12
    0.17
    393
    +0.12
    0.25
    Negative Logits
     exorc
    -0.84
    emonium
    -0.82
    ³³³
    -0.77
     occas
    -0.77
     pneum
    -0.76
     malaria
    -0.74
     Takeru
    -0.74
     deserts
    -0.72
     elect
    -0.71
     inher
    -0.70
    POSITIVE LOGITS
    #$
    1.52
    realDonaldTrump
    1.47
    gmail
    1.01
    wik
    0.97
    twitter
    0.95
    IB
    0.95
    said
    0.94
    YouTube
    0.93
    GS
    0.92
    lat
    0.92
    Activations Density 8.879%

    No Known Activations