© 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. 6-RES-JB
    11. 15432
    Prev
    Next
    INDEX
    Explanations

    mentions of witch hunts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of witch hunts and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ais
    -0.85
    oulos
    -0.84
    roit
    -0.78
    anian
    -0.74
    obal
    -0.73
    undo
    -0.73
    raltar
    -0.73
    ittal
    -0.73
    ateral
    -0.72
    arian
    -0.72
    POSITIVE LOGITS
     haz
    1.01
    doctor
    1.01
    crow
    0.94
    pload
    0.83
     witch
    0.82
     hunts
    0.79
     Witch
    0.78
     Hazel
    0.78
    hunt
    0.75
    ãĥ£
    0.75
    Activations Density 0.034%

    No Known Activations