© 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. 11354
    Prev
    Next
    INDEX
    Explanations

    words related to causing controversy or heated reactions

    oai_token-act-pair · gpt-3.5-turbo

    words related to provoking or inciting reactions or debates

    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
    ©¶æ
    -0.78
    aver
    -0.74
     Accounting
    -0.74
    iances
    -0.73
    fficiency
    -0.73
    ithing
    -0.71
    lying
    -0.70
    arent
    -0.67
    alach
    -0.67
    enfranch
    -0.65
    POSITIVE LOGITS
     provoke
    1.38
     provocation
    1.26
     provoked
    1.16
     provoking
    1.15
     bystanders
    0.94
    xual
    0.92
     arous
    0.91
     escalation
    0.90
     prompt
    0.85
     inciting
    0.85
    Activations Density 0.016%

    No Known Activations