© 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. 8-RES-JB
    11. 9879
    Prev
    Next
    INDEX
    Explanations

    dates in various formats

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Glac
    -0.67
     centrif
    -0.59
     resil
    -0.58
    dor
    -0.56
     glaciers
    -0.54
     Liberties
    -0.52
     humid
    -0.50
     stranded
    -0.50
     landfill
    -0.50
     pixels
    -0.49
    POSITIVE LOGITS
    escription
    0.75
    iquette
    0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.66
     acknowled
    0.64
    Accessory
    0.63
    acea
    0.62
    viation
    0.61
    £ı
    0.60
     Cosponsors
    0.59
     substitution
    0.58
    Activations Density 1.456%

    No Known Activations