© 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. 11423
    Prev
    Next
    INDEX
    Explanations

    descriptions of financial numbers and significant figures within text

    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
    690
    +0.11
    0.4%
    490
    +0.11
    0.4%
    540
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.11
    0.08
    671
    +0.11
    0.07
    540
    +0.11
    0.11
    Negative Logits
    dimension
    -1.02
    moil
    -0.86
    isner
    -0.85
    dor
    -0.83
    hover
    -0.82
    onding
    -0.81
    ictions
    -0.74
    pter
    -0.73
    afety
    -0.73
    ravings
    -0.73
    POSITIVE LOGITS
     considering
    1.00
     understatement
    0.94
     omission
    0.93
     coincidence
    0.90
     indeed
    0.88
     huh
    0.86
     compared
    0.84
     accomplishment
    0.78
    PLIED
    0.78
     hypocrisy
    0.73
    Activations Density 2.450%

    No Known Activations