© 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. 6231
    Prev
    Next
    INDEX
    Explanations

    instances regarding specific engineering terms like 'diverging' and 'diverging', especially in the context of construction and planning projects

    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
    167
    +0.19
    0.7%
    549
    +0.19
    0.6%
    232
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.13
    326
    +0.19
    0.09
    537
    +0.17
    0.07
    Negative Logits
    Laughs
    -0.99
    ellen
    -0.96
    DOC
    -0.94
    EEK
    -0.94
    oke
    -0.94
    hel
    -0.93
    Owner
    -0.91
    EV
    -0.91
    waukee
    -0.85
    Edited
    -0.85
    POSITIVE LOGITS
    gent
    1.51
    ging
    1.50
    gencies
    1.48
    ministic
    1.46
    gence
    1.38
    gently
    1.20
    lations
    1.20
    ulent
    1.20
    gency
    1.17
    ged
    1.15
    Activations Density 1.429%

    No Known Activations