© 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. 21503
    Prev
    Next
    INDEX
    Explanations

    prompts related to taking actions or participating in activities

    oai_token-act-pair · gpt-3.5-turbo

    repetitive structures or phrases that emphasize actions

    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
    Reviewer
    -0.62
    want
    -0.60
    ommel
    -0.59
    enegger
    -0.57
    omething
    -0.56
     psychiat
    -0.56
    uits
    -0.55
     dissatisf
    -0.55
    kens
    -0.54
    redients
    -0.54
    POSITIVE LOGITS
    ILA
    0.66
    MAG
    0.60
    LIB
    0.59
    ¶ħ
    0.54
     LAR
    0.53
     Resistance
    0.51
    ESH
    0.50
    radius
    0.49
     Blessing
    0.48
    Hand
    0.47
    Activations Density 0.060%

    No Known Activations