© 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. 2-RES-JB
    11. 9149
    Prev
    Next
    INDEX
    Explanations

    references to witches or witchcraft

    oai_token-act-pair · gpt-3.5-turbo

    references to witches and witchcraft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egal
    -0.83
    inished
    -0.79
    ournal
    -0.74
    ributed
    -0.74
    served
    -0.72
    rained
    -0.72
    upon
    -0.68
    rez
    -0.66
    jri
    -0.66
    haar
    -0.66
    POSITIVE LOGITS
     Witch
    1.00
    doctor
    0.95
     witch
    0.86
     hunts
    0.81
     haz
    0.81
     Hazel
    0.79
    witch
    0.78
     CLSID
    0.76
    ERY
    0.76
    ãĥīãĥ©
    0.75
    Activations Density 0.011%

    No Known Activations