© 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. 1-RES-JB
    11. 16827
    Prev
    Next
    INDEX
    Explanations

    verbs related to reversal or alteration

    oai_token-act-pair · gpt-3.5-turbo

    references to actions of reversing or canceling previous decisions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ategories
    -0.86
    oak
    -0.85
    croft
    -0.77
    fighter
    -0.74
    azines
    -0.73
    metics
    -0.72
    android
    -0.70
    medium
    -0.70
    colo
    -0.69
    raq
    -0.69
    POSITIVE LOGITS
     undo
    1.28
    undo
    1.07
     undone
    1.02
     undermin
    0.77
     revers
    0.73
    ĸļ
    0.72
    issance
    0.72
     wrench
    0.71
     erase
    0.70
     miracles
    0.70
    Activations Density 0.006%

    No Known Activations