© 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. 10961
    Prev
    Next
    INDEX
    Explanations

    specifically, phrases starting with "For one thing," and variations thereof

    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
    650
    +0.19
    0.6%
    71
    +0.17
    0.5%
    581
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.19
    0.06
    71
    +0.17
    0.03
    691
    +0.16
    0.04
    Negative Logits
    ocracy
    -0.98
    ocrats
    -0.96
    buff
    -0.95
    dal
    -0.92
    ornia
    -0.92
    ocated
    -0.89
    owed
    -0.89
    ãĤ´ãĥ³
    -0.88
    ready
    -0.87
    ãĤ¹ãĥĪ
    -0.86
    POSITIVE LOGITS
     sake
    1.53
     reasons
    1.08
    hesda
    0.96
     purposes
    0.96
     ILCS
    0.92
     hundred
    0.92
     cents
    0.88
     reason
    0.87
     relief
    0.86
     Alc
    0.84
    Activations Density 0.750%

    No Known Activations