© 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. 8671
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or movies in the X-Men franchise

    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
    649
    +0.20
    0.6%
    578
    +0.18
    0.6%
    525
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.20
    0.04
    525
    +0.18
    0.05
    659
    +0.18
    0.04
    Negative Logits
    kson
    -1.47
    kamp
    -1.27
    getic
    -1.24
     captcha
    -1.20
    Ú
    -1.19
     Lauder
    -1.15
    inally
    -1.13
    ufact
    -1.11
    Downloadha
    -1.08
    sburgh
    -1.07
    POSITIVE LOGITS
    avier
    1.76
    posed
    1.62
    peria
    1.49
    IX
    1.41
    XXXX
    1.40
    iao
    1.34
    yz
    1.33
    TERN
    1.28
     chromosome
    1.21
    cellence
    1.20
    Activations Density 0.638%

    No Known Activations