© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11201
    Prev
    Next
    INDEX
    Explanations

    references to small quantities or degrees

    oai_token-act-pair · gpt-3.5-turbo

    variations of the phrase "a little" indicating small amounts or degrees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.91
    eneg
    -0.81
    ourses
    -0.78
    orthy
    -0.77
    emale
    -0.74
    idents
    -0.73
    ayn
    -0.72
    views
    -0.72
    yss
    -0.72
    ufact
    -0.71
    POSITIVE LOGITS
     bit
    1.55
     BIT
    0.91
     girl
    0.82
     extra
    0.79
     Bit
    0.79
     peek
    0.78
     tad
    0.77
     somet
    0.76
     kid
    0.75
    bit
    0.75
    Activations Density 0.041%

    No Known Activations