© 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 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. 33228
    Prev
    Next
    INDEX
    Explanations

    quotes from interviews or articles

    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
    160
    +0.16
    0.8%
    640
    +0.16
    0.8%
    447
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.16
    0.26
    184
    +0.16
    0.04
    173
    +0.14
    0.07
    Negative Logits
     Leilan
    -0.76
     buoy
    -0.70
     lav
    -0.70
     benefic
    -0.67
     dense
    -0.66
     inund
    -0.65
    quished
    -0.65
     sparing
    -0.64
     ener
    -0.64
     orn
    -0.63
    POSITIVE LOGITS
    sic
    1.62
    laughs
    1.34
    âĢ¦)
    1.29
    emphasis
    1.16
    ...)
    1.16
    Laughs
    1.10
    GB
    0.98
    meaning
    0.98
    around
    0.92
    blank
    0.92
    Activations Density 10.769%

    No Known Activations