© 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. 8006
    Prev
    Next
    INDEX
    Explanations

    phrases related to a particular person's name, specifically "Clegg."

    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
    289
    +0.16
    0.6%
    420
    +0.15
    0.5%
    615
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.09
    326
    +0.15
    0.07
    588
    +0.14
    0.06
    Negative Logits
    yrinth
    -1.02
    ournals
    -0.91
    SG
    -0.88
    uates
    -0.87
    ãĥ¼ãĥĨãĤ£
    -0.85
    icum
    -0.83
    utm
    -0.83
     Helsinki
    -0.82
    URI
    -0.81
    orsi
    -0.80
    POSITIVE LOGITS
    arest
    1.35
    avage
    1.28
    veland
    1.12
    combe
    1.12
    aving
    1.09
    lean
    1.06
    arer
    1.02
    avement
    1.02
    cles
    1.01
    aved
    1.01
    Activations Density 1.022%

    No Known Activations