© 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. 7852
    Prev
    Next
    INDEX
    Explanations

    situations involving conflicting actions or decisions by individuals

    oai_token-act-pair · gpt-3.5-turbo

    emotional responses and actions related to fear and apprehension

    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
    acea
    -0.68
    ablishment
    -0.66
    orthy
    -0.63
     Expect
    -0.61
    hap
    -0.60
    hart
    -0.59
     exempl
    -0.57
    escent
    -0.56
     ILCS
    -0.56
     Benefits
    -0.56
    POSITIVE LOGITS
     vetoed
    1.03
     instead
    1.02
    instead
    1.00
     refused
    0.98
     balk
    0.97
     postponed
    0.93
     overr
    0.93
     mysteriously
    0.91
     alas
    0.90
     never
    0.89
    Activations Density 0.464%

    No Known Activations