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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14850
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical actions and bodily reactions

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of traumatic or violent events

    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
     Inher
    -0.82
     Patreon
    -0.80
     virtues
    -0.79
     merits
    -0.77
     Founders
    -0.76
     Bonus
    -0.75
     Architects
    -0.73
     constituencies
    -0.73
    ãĤ´ãĥ³
    -0.71
    ģĸ
    -0.70
    POSITIVE LOGITS
     panicked
    1.06
     ..."
    1.01
    ,'"
    0.99
     gunshots
    0.98
     yelling
    0.97
     scared
    0.96
     smelled
    0.95
     âĢ¦"
    0.95
     screaming
    0.93
    ..."
    0.90
    Activations Density 0.719%

    No Known Activations