© 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 Local
    9. 6-RES_SCL-AJT
    11. 34897
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Doug" in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.14
    0.7%
    339
    +0.12
    0.6%
    208
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    60
    +0.14
    0.08
    162
    +0.12
    0.08
    211
    +0.12
    -0.01
    Negative Logits
    istic
    -0.70
    */(
    -0.70
    Interstitial
    -0.69
     Tend
    -0.68
    iferation
    -0.67
    istical
    -0.64
    itia
    -0.63
    mberg
    -0.63
    CVE
    -0.63
    tsky
    -0.62
    POSITIVE LOGITS
    herty
    1.46
    ards
    0.98
    aneers
    0.84
     Ell
    0.84
    arded
    0.82
    ords
    0.80
     Fir
    0.78
     Doug
    0.77
    ARDS
    0.76
    ard
    0.75
    Activations Density 8.051%

    No Known Activations