© 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. 2638
    Prev
    Next
    INDEX
    Explanations

    words related to specific technological actions or equipment

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to specific actionable items or technology

    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
    creen
    -0.79
    cale
    -0.78
    ervative
    -0.74
    outhern
    -0.74
     redistributed
    -0.71
    ilk
    -0.70
    risome
    -0.68
    etter
    -0.65
    ãĤ±
    -0.65
    hetto
    -0.64
    POSITIVE LOGITS
    lets
    1.10
    ologies
    1.06
    ages
    0.98
    plates
    0.93
    worms
    0.93
    naires
    0.92
    backs
    0.88
    ings
    0.88
    cases
    0.87
     holders
    0.87
    Activations Density 0.777%

    No Known Activations