© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11086
    Prev
    Next
    INDEX
    Explanations

    names of brands or products

    oai_token-act-pair · gpt-3.5-turbo

    references to popular brands and products

    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
    ousands
    -0.66
    ictions
    -0.59
    stories
    -0.59
    acterial
    -0.58
    missions
    -0.57
     distractions
    -0.56
    yss
    -0.55
     refunds
    -0.55
     microbiota
    -0.55
     microbiome
    -0.54
    POSITIVE LOGITS
    *.
    0.76
    .]
    0.76
    !.
    0.76
    .[
    0.75
    _.
    0.75
    .
    0.74
    .)
    0.73
     circa
    0.70
    .(
    0.69
     followed
    0.67
    Activations Density 0.729%

    No Known Activations