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. 0-RES-JB
    6. 5629
    Prev
    Next
    INDEX
    Explanations

    mentions of physical medical conditions, such as "diarrhoea."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific materials or components related to identity and labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cour
    -0.72
     drib
    -0.68
     euph
    -0.65
     Courts
    -0.64
     gam
    -0.63
    phan
    -0.62
     Dhabi
    -0.61
     anthem
    -0.60
     penn
    -0.59
    yright
    -0.59
    POSITIVE LOGITS
     Leather
    1.83
    hoe
    1.23
    yip
    0.95
    idth
    0.84
    °
    0.74
     Knot
    0.73
     Huck
    0.72
    haul
    0.71
     Michaels
    0.70
    chwitz
    0.70
    Activations Density 0.010%

    No Known Activations