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. 10-RES-JB
    6. 9613
    Prev
    Next
    INDEX
    Explanations

    keywords related to font types and typography

    oai_token-act-pair · gpt-3.5-turbo

    references to different types or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leaks
    -0.65
     Bills
    -0.64
     Morning
    -0.63
    å§«
    -0.63
    iae
    -0.61
    romeda
    -0.61
    ahar
    -0.61
    eor
    -0.61
     Bots
    -0.60
    nesday
    -0.60
    POSITIVE LOGITS
    face
    1.49
    faces
    1.47
    casting
    1.20
    ahead
    1.16
    etting
    1.15
    cast
    1.07
    etter
    1.07
    classes
    0.95
    alias
    0.89
    casts
    0.85
    Activations Density 0.037%

    No Known Activations