© 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. 1-RES-JB
    11. 21787
    Prev
    Next
    INDEX
    Explanations

    quotations from media related to opposing the status quo

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce additional ideas or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     millenn
    -0.78
    åĪ
    -0.78
     Purg
    -0.76
     Homs
    -0.69
     Gou
    -0.68
     Horus
    -0.64
    today
    -0.63
    %]
    -0.62
     Lup
    -0.62
    å¦
    -0.61
    POSITIVE LOGITS
    laws
    0.77
    coe
    0.77
    idth
    0.66
    rium
    0.65
    iscons
    0.63
    strate
    0.62
    ICO
    0.62
    commit
    0.61
     Fundamental
    0.61
    ometown
    0.60
    Activations Density 0.000%

    No Known Activations