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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 21198
    Prev
    Next
    INDEX
    Explanations

    mentions of academic classes, with a focus on math classes specifically

    oai_token-act-pair · gpt-3.5-turbo

    mentions of classes and educational settings

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

    No Comments

    Negative Logits
    orthy
    -0.76
     porous
    -0.74
     viral
    -0.68
    vernment
    -0.65
     mutated
    -0.62
     spurious
    -0.61
    ossier
    -0.61
    edia
    -0.60
    obar
    -0.60
     plausible
    -0.59
    POSITIVE LOGITS
    ifications
    1.04
    ifiers
    0.97
    classes
    0.94
    ifies
    0.91
    room
    0.90
    ifier
    0.89
    anova
    0.86
    mates
    0.85
    ifying
    0.83
    rooms
    0.80
    Activations Density 0.017%

    No Known Activations