© 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. 183
    Prev
    Next
    INDEX
    Explanations

    patterns of letters 'up' followed by another letter, with increasing activation for longer patterns starting with 'up'

    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
    140
    +0.17
    0.6%
    447
    +0.15
    0.6%
    481
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.01
    107
    +0.15
    0.01
    477
    +0.13
    0.01
    Negative Logits
     Ryder
    -0.85
    Ban
    -0.85
    inav
    -0.84
    Marie
    -0.83
    ÃŃn
    -0.83
    76561
    -0.80
    vest
    -0.78
    Interstitial
    -0.77
    ieth
    -0.73
    720
    -0.73
    POSITIVE LOGITS
    £ı
    0.80
    zhou
    0.79
    agall
    0.76
    gorith
    0.76
     machinery
    0.74
     Chimera
    0.69
    perty
    0.69
    worms
    0.68
     fit
    0.66
     Orion
    0.66
    Activations Density 0.021%

    No Known Activations