© 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. 11-RES-JB
    11. 20587
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating a specific position or condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases that signify being in a critical or precarious situation

    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
    ividual
    -0.71
    ns
    -0.69
    resso
    -0.68
    zona
    -0.66
    ensis
    -0.65
    ecause
    -0.62
    Bey
    -0.62
    initions
    -0.59
    yne
    -0.58
    Gray
    -0.58
    POSITIVE LOGITS
     track
    1.09
     edge
    0.99
     pace
    0.99
     shaky
    0.98
     verge
    0.95
     course
    0.94
     brink
    0.87
    track
    0.86
     cue
    0.83
     hiatus
    0.83
    Activations Density 0.053%

    No Known Activations