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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 18746
    Prev
    Next
    INDEX
    Explanations

    instances where there is mention of being just one part of a group or collection

    oai_token-act-pair · gpt-3.5-turbo

    instances of stating something as a singular example or case among many

    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
    lean
    -0.72
    sleep
    -0.67
    alty
    -0.65
    ISO
    -0.65
     ç¥ŀ
    -0.64
    ancies
    -0.62
    lav
    -0.60
    elo
    -0.60
    ãĥİ
    -0.60
    luaj
    -0.59
    POSITIVE LOGITS
     scratching
    0.79
     facet
    0.77
    Ware
    0.77
     examples
    0.73
     scratched
    0.68
     sympt
    0.67
    £ı
    0.67
     scratches
    0.66
    yk
    0.64
     facets
    0.64
    Activations Density 0.125%

    No Known Activations