© 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 Local
    9. 6-RES_SCL-AJT
    11. 36296
    Prev
    Next
    INDEX
    Explanations

    specifically mentioned points or details within a broader context

    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
    449
    +0.09
    0.5%
    101
    +0.09
    0.5%
    43
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    602
    +0.09
    0.13
    598
    +0.09
    0.09
    267
    +0.09
    0.14
    Negative Logits
     unbeat
    -0.59
    arthed
    -0.55
    ]"
    -0.54
    unts
    -0.54
    pez
    -0.54
    mage
    -0.50
     wheelchair
    -0.49
     decaying
    -0.48
     undergone
    -0.48
    )",
    -0.47
    POSITIVE LOGITS
    poons
    0.59
     importantly
    0.58
    dylib
    0.57
    ŀ
    0.56
    acio
    0.55
     Facts
    0.54
     Strategies
    0.54
    entimes
    0.54
    noon
    0.53
    chio
    0.53
    Activations Density 7.926%

    No Known Activations