© 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. 22204
    Prev
    Next
    INDEX
    Explanations

    mentions of live-action content or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to live-action content and streaming

    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
    selage
    -0.70
    Īè
    -0.68
     favored
    -0.67
     favoured
    -0.65
     aster
    -0.65
    ierre
    -0.64
     Fiorina
    -0.64
     curve
    -0.63
     favoring
    -0.62
     defences
    -0.61
    POSITIVE LOGITS
    stream
    0.92
    atten
    0.89
    reality
    0.87
    motion
    0.83
    blogs
    0.80
    flo
    0.80
    lance
    0.79
    action
    0.79
    chat
    0.79
    trial
    0.78
    Activations Density 0.055%

    No Known Activations