© 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. 11605
    Prev
    Next
    INDEX
    Explanations

    names of individuals named "Roy" that are mentioned in a text

    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
    326
    +0.21
    0.7%
    746
    +0.17
    0.5%
    35
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.10
    288
    +0.17
    0.11
    659
    +0.17
    0.07
    Negative Logits
    iphany
    -1.04
     Indones
    -1.03
     Disorder
    -0.97
    oenix
    -0.94
     TSA
    -0.90
     NIC
    -0.89
    ablishment
    -0.89
     oper
    -0.88
    atform
    -0.87
    ospital
    -0.87
    POSITIVE LOGITS
    alties
    2.09
    ce
    1.47
    ston
    1.34
    dy
    1.25
    hips
    1.18
     Hodg
    1.11
    dies
    1.11
     Roy
    1.11
    der
    1.11
    cers
    1.09
    Activations Density 1.832%

    No Known Activations