© 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 EvalsExportsinterp-engineNEWAPI 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. 10977
    Prev
    Next
    INDEX
    Explanations

    comparisons or expressions of preference

    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
    14
    +0.15
    0.5%
    647
    +0.13
    0.5%
    373
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    692
    +0.15
    0.05
    647
    +0.13
    0.05
    546
    +0.13
    0.06
    Negative Logits
    tein
    -1.04
    cill
    -1.04
    ennes
    -0.98
    atform
    -0.97
    rity
    -0.97
    rete
    -0.95
    iets
    -0.95
    alogue
    -0.95
    apers
    -0.94
    aley
    -0.94
    POSITIVE LOGITS
    lihood
    2.06
    lier
    1.49
    liest
    1.46
    liness
    1.14
    minded
    1.08
     clock
    0.97
     wildfire
    0.92
    ability
    0.88
     minded
    0.87
    ly
    0.84
    Activations Density 0.697%

    No Known Activations