© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 10470
    Prev
    Next
    INDEX
    Explanations

    terms related to support or advocacy

    oai_token-act-pair · gpt-3.5-turbo

    references to support or advocacy groups, particularly those related to the "Supp" theme

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    puter
    -0.83
    gger
    -0.83
    Du
    -0.78
    FG
    -0.76
     Wilde
    -0.74
     Cage
    -0.71
    df
    -0.71
    ixels
    -0.68
    JB
    -0.67
    ATHER
    -0.67
    POSITIVE LOGITS
     Shooter
    0.76
    esi
    0.75
     Himal
    0.72
    s
    0.72
    utical
    0.72
    iant
    0.71
     Vendor
    0.71
     wip
    0.71
     Reviews
    0.68
    visors
    0.66
    Activations Density 0.018%

    No Known Activations