© 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. 1-RES-JB
    11. 21777
    Prev
    Next
    INDEX
    Explanations

    the word "Dill"

    oai_token-act-pair · gpt-3.5-turbo

    names and terms associated with specific brands or significant entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ould
    -0.76
    hew
    -0.72
    76561
    -0.71
    istration
    -0.70
    psons
    -0.67
    izo
    -0.66
    ambo
    -0.66
    atted
    -0.65
    sburgh
    -0.64
     automate
    -0.63
    POSITIVE LOGITS
    gence
    0.82
    ministic
    0.78
    Pad
    0.78
     contrace
    0.76
     Caller
    0.70
    IVERS
    0.70
     Domain
    0.69
    ependent
    0.67
    sense
    0.67
     Prin
    0.66
    Activations Density 0.060%

    No Known Activations