© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 2036
    Prev
    Next
    INDEX
    Explanations

    keywords related to identification and recognition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "identify" related to investigations and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cour
    -0.68
    cour
    -0.67
     Heaven
    -0.67
     cush
    -0.66
    ta
    -0.64
    flation
    -0.63
    oz
    -0.63
     Tonight
    -0.61
     Glass
    -0.61
     Coup
    -0.58
    POSITIVE LOGITS
     identify
    3.27
     identifies
    2.28
     identifying
    2.20
     identified
    1.92
     identification
    1.80
     Ident
    1.76
    Ident
    1.61
     recognize
    1.52
    identified
    1.52
     locate
    1.50
    Activations Density 0.016%

    No Known Activations