© 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. 10553
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to narrating actions and dialogue in a narrative

    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
    551
    +0.13
    0.5%
    167
    +0.12
    0.5%
    393
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.13
    0.12
    551
    +0.12
    0.11
    477
    +0.12
    0.08
    Negative Logits
    aye
    -0.82
    their
    -0.81
    fect
    -0.79
    casts
    -0.79
     theirs
    -0.77
     THEM
    -0.77
    cum
    -0.75
    ////////////////////////////////
    -0.74
    obia
    -0.74
    mire
    -0.73
    POSITIVE LOGITS
    're
    1.05
    'll
    0.94
    'd
    0.85
     helicop
    0.79
    DragonMagazine
    0.73
    've
    0.73
    abba
    0.72
    IRD
    0.71
    oros
    0.71
    atically
    0.71
    Activations Density 1.678%

    No Known Activations