© 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. 12329
    Prev
    Next
    INDEX
    Explanations

    mentions of founders or creators of various organizations, companies or projects

    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
    288
    +0.22
    0.7%
    679
    +0.19
    0.6%
    727
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.06
    541
    +0.19
    0.05
    414
    +0.16
    0.04
    Negative Logits
    othy
    -1.11
     Ukrain
    -1.05
    hap
    -1.03
    pered
    -1.02
    anche
    -1.01
    uters
    -0.99
    essage
    -0.97
    oles
    -0.97
    alle
    -0.95
    obe
    -0.94
    POSITIVE LOGITS
    founder
    1.24
    doms
    1.24
     Ezra
    1.23
    strate
    1.15
    camp
    1.11
     Fathers
    1.10
    ãĥ¼ãĥĨãĤ£
    1.10
    lisher
    1.10
     Dayton
    1.08
     founder
    1.06
    Activations Density 0.596%

    No Known Activations