© 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. 11434
    Prev
    Next
    INDEX
    Explanations

    mentions of specific parking-related terms and infrastructure

    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
    +0.23
    0.9%
    570
    +0.14
    0.5%
    538
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.11
    326
    +0.14
    0.08
    415
    +0.13
    0.05
    Negative Logits
    Downloadha
    -1.35
    xual
    -1.20
    vous
    -0.96
    nces
    -0.96
     Flavoring
    -0.95
    gui
    -0.92
     Grimm
    -0.92
    akuya
    -0.90
    anson
    -0.87
    ural
    -0.86
    POSITIVE LOGITS
     garage
    1.29
    lot
    1.22
     attendants
    1.04
     parking
    1.01
    wagon
    0.99
     leases
    0.98
     brake
    0.97
     Garage
    0.97
    conservancy
    0.95
    holders
    0.94
    Activations Density 1.460%

    No Known Activations