© 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. 13303
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and dealings

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and grammatical constructs within the text

    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
    ividual
    -0.74
    ecause
    -0.61
    irlf
    -0.55
    ogun
    -0.52
    athered
    -0.51
    itially
    -0.51
    ruary
    -0.50
    mosp
    -0.49
     ItemLevel
    -0.49
     "$:/
    -0.48
    POSITIVE LOGITS
    .
    0.99
    ,
    0.94
    ;
    0.70
    .,
    0.68
    .]
    0.65
    EStream
    0.62
    ,...
    0.62
    -
    0.61
     antioxid
    0.60
    ."
    0.60
    Activations Density 3.032%

    No Known Activations