© 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. 6792
    Prev
    Next
    INDEX
    Explanations

    forward-looking statements and associated risks and uncertainties in corporate documents

    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
    641
    +0.15
    0.6%
    590
    +0.12
    0.5%
    103
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.15
    0.03
    247
    +0.12
    0.02
    556
    +0.12
    0.02
    Negative Logits
    DERR
    -0.99
    ACP
    -0.93
    Interstitial
    -0.91
    RGB
    -0.82
    ELY
    -0.77
    ACTED
    -0.76
    âĹ¼
    -0.76
    RP
    -0.74
     deviation
    -0.73
    bourg
    -0.73
    POSITIVE LOGITS
    ogle
    0.78
     predic
    0.73
     Andersen
    0.68
     Piper
    0.68
    ucker
    0.67
    itta
    0.66
    roll
    0.66
    reath
    0.65
    anger
    0.64
     mindfulness
    0.64
    Activations Density 0.145%

    No Known Activations