© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 4345
    Prev
    Next
    INDEX
    Explanations

    specific locations or addresses

    oai_token-act-pair · gpt-3.5-turbo

    locations and times related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    board
    -0.64
     environments
    -0.59
     boards
    -0.58
     slic
    -0.58
     surfaces
    -0.57
    hops
    -0.56
     chests
    -0.55
     sails
    -0.55
     pits
    -0.54
     habitats
    -0.54
    POSITIVE LOGITS
    ĸļ
    0.81
    capital
    0.67
     Discount
    0.63
    =]
    0.63
    rium
    0.62
    las
    0.60
    AAAA
    0.60
    utor
    0.60
     Irving
    0.59
     Noon
    0.59
    Activations Density 0.150%

    No Known Activations