© 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. 9-RES-JB
    11. 15750
    Prev
    Next
    INDEX
    Explanations

    phrases related to causing controversy or strong reactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with provocation and public outrage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tags
    -0.82
    models
    -0.77
    Rules
    -0.75
    parts
    -0.75
    coins
    -0.74
    arte
    -0.74
    words
    -0.74
    rics
    -0.72
    sheets
    -0.71
    ãĤ¢ãĥ«
    -0.70
    POSITIVE LOGITS
     lot
    1.17
     flurry
    1.07
    rouse
    1.05
     plethora
    1.05
     hefty
    1.04
     barrage
    1.02
     slew
    1.02
     lengthy
    1.00
     resurgence
    0.98
     reversal
    0.97
    Activations Density 0.265%

    No Known Activations