Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 20504
    Prev
    Next
    INDEX
    Explanations

    options or choices that fit a given situation or circumstance

    oai_token-act-pair · gpt-3.5-turbo

    options or choices relevant to individual needs or preferences

    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
    comings
    -0.72
    enture
    -0.72
    ĸļ
    -0.71
    ensive
    -0.71
    İĭ
    -0.70
    icken
    -0.70
    ©¶æ¥µ
    -0.70
    isse
    -0.69
    pread
    -0.65
    ework
    -0.63
    POSITIVE LOGITS
     corresponds
    1.15
     closest
    0.93
     nearest
    0.93
     best
    0.86
     suited
    0.79
     suits
    0.79
     safest
    0.78
     fits
    0.77
     strongest
    0.77
     lowest
    0.76
    Activations Density 0.331%

    No Known Activations