© 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. 8-RES-JB
    11. 22303
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Smith" in a document

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Smith."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADRA
    -0.76
    ktop
    -0.67
    ça
    -0.64
    stract
    -0.62
    ATING
    -0.62
    UGE
    -0.61
    ctory
    -0.60
     Greenpeace
    -0.58
    PDATE
    -0.58
     sympt
    -0.58
    POSITIVE LOGITS
    sonian
    1.68
    son
    0.98
    sburg
    0.92
     Barney
    0.89
    smanship
    0.89
    ies
    0.87
    gren
    0.86
    anity
    0.84
    field
    0.84
    inelli
    0.84
    Activations Density 0.022%

    No Known Activations