© 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. 4-RES-JB
    11. 7339
    Prev
    Next
    INDEX
    Explanations

    verbs related to instigating actions or reactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to provocation and its consequences

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

    No Comments

    Negative Logits
    oard
    -0.75
     Accounting
    -0.74
    aver
    -0.71
    aum
    -0.71
    league
    -0.70
    ultz
    -0.70
    ayer
    -0.69
    ithing
    -0.69
    olitan
    -0.67
    amacare
    -0.67
    POSITIVE LOGITS
     provocation
    1.25
     provoke
    1.14
     provoking
    1.02
     provoked
    0.95
     provocative
    0.91
    xual
    0.90
     bystanders
    0.90
     prov
    0.81
     laughter
    0.80
     prompt
    0.80
    Activations Density 0.018%

    No Known Activations