© 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. 1886
    Prev
    Next
    INDEX
    Explanations

    news headlines related to current events and social issues

    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
    373
    +0.16
    0.5%
    519
    +0.15
    0.5%
    610
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.16
    0.02
    185
    +0.15
    0.01
    739
    +0.13
    0.01
    Negative Logits
    abol
    -1.19
    ministic
    -1.04
    atana
    -1.02
    omsky
    -1.01
    axis
    -1.00
    romy
    -0.94
    aido
    -0.92
    road
    -0.91
     theoret
    -0.91
     independ
    -0.90
    POSITIVE LOGITS
     Caption
    1.29
     Close
    1.20
     largeDownload
    1.09
     Loading
    1.04
     Gallery
    1.03
    iffe
    1.01
     Scenes
    1.01
     Shutdown
    1.00
    Thumbnail
    0.97
     galleries
    0.96
    Activations Density 0.015%

    No Known Activations