© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 3237
    Prev
    Next
    INDEX
    Explanations

    names of characters or individuals named Cody

    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
    356
    +0.07
    0.5%
    568
    +0.07
    0.5%
    284
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.07
    0.08
    288
    +0.07
    0.10
    659
    +0.07
    0.06
    Negative Logits
    obar
    -0.48
    rior
    -0.44
     Inquisition
    -0.43
     fries
    -0.41
     payable
    -0.41
    ordinate
    -0.40
    usher
    -0.40
    erences
    -0.40
    raged
    -0.40
     lion
    -0.39
    POSITIVE LOGITS
    NetMessage
    0.62
    bilt
    0.59
    nia
    0.56
    lus
    0.54
    obyl
    0.53
    nces
    0.53
    nian
    0.52
    gdala
    0.52
    EStream
    0.51
    lia
    0.50
    Activations Density 0.949%

    No Known Activations