© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1833
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    651
    +0.24
    0.8%
    311
    +0.21
    0.7%
    554
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.24
    0.11
    326
    +0.21
    0.09
    232
    +0.18
    0.07
    Negative Logits
    daq
    -1.25
    ãĥ£
    -1.16
    EStream
    -1.08
     ILCS
    -1.03
    SHIP
    -1.02
    inventoryQuantity
    -1.02
    esthetic
    -1.02
    ————————
    -1.01
    ntax
    -1.01
    PLA
    -0.99
    POSITIVE LOGITS
    itude
    1.59
    ificate
    1.53
    iary
    1.53
    ieth
    1.42
    ruck
    1.41
    endon
    1.40
    ickets
    1.37
    ures
    1.32
    ogether
    1.32
    aining
    1.27
    Activations Density 1.688%

    No Known Activations