© 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. 11-RES-JB
    11. 15676
    Prev
    Next
    INDEX
    Explanations

    instances of quick movement or escape

    oai_token-act-pair · gpt-3.5-turbo

    actions of running or fleeing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artisan
    -0.75
    olia
    -0.74
    ortium
    -0.68
    repre
    -0.68
    orum
    -0.60
    Birth
    -0.57
     defic
    -0.57
     Publication
    -0.56
    urers
    -0.56
     enshr
    -0.55
    POSITIVE LOGITS
     away
    1.09
    nin
    1.06
    aways
    1.02
     hither
    1.00
    away
    0.98
     err
    0.97
     awa
    0.95
    gs
    0.92
     screaming
    0.88
     downhill
    0.87
    Activations Density 0.057%

    No Known Activations