© 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. 8681
    Prev
    Next
    INDEX
    Explanations

    locations or events in a document

    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
    247
    +0.15
    0.5%
    267
    +0.15
    0.5%
    34
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.15
    0.01
    247
    +0.15
    0.01
    518
    +0.13
    0.02
    Negative Logits
     Dynamics
    -1.15
    ovan
    -0.94
     Noir
    -0.90
     Elastic
    -0.86
     Wooden
    -0.84
     Myster
    -0.84
     Diver
    -0.83
    illon
    -0.80
     Instr
    -0.78
    eele
    -0.77
    POSITIVE LOGITS
    _.
    0.96
    _-
    0.96
    itude
    0.94
    dict
    0.92
    /_
    0.90
    SOURCE
    0.86
    ""
    0.85
    ilities
    0.85
    ighty
    0.84
    claim
    0.83
    Activations Density 0.145%

    No Known Activations