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. 23629
    Prev
    Next
    INDEX
    Explanations

    people's names and locations, possibly related to a political or historical context

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "iso."

    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
     regress
    -0.78
     Radar
    -0.73
     crafts
    -0.69
     craft
    -0.68
     Defensive
    -0.64
     MVP
    -0.64
     tick
    -0.63
     patent
    -0.61
     radar
    -0.61
     AW
    -0.60
    POSITIVE LOGITS
    iso
    4.63
    ibu
    1.61
    ISO
    1.32
    izo
    1.31
    resa
    1.28
    esar
    1.28
    illin
    1.26
    hex
    1.22
    agus
    1.13
    enda
    1.13
    Activations Density 0.027%

    No Known Activations