© 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. 0-RES-JB
    11. 8380
    Prev
    Next
    INDEX
    Explanations

    words related to the action of writing strokes or movements

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or entities associated with 'kes'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     number
    -0.69
     ANC
    -0.64
     å
    -0.64
     needless
    -0.61
     home
    -0.61
    Home
    -0.59
     Number
    -0.58
     expanding
    -0.58
     MVP
    -0.58
     Ricardo
    -0.57
    POSITIVE LOGITS
    kes
    4.49
    ke
    2.09
    kens
    1.92
    kers
    1.62
    ken
    1.59
    kins
    1.50
    kos
    1.47
    ked
    1.46
    king
    1.44
    ker
    1.42
    Activations Density 0.010%

    No Known Activations