© 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. 9-RES-JB
    11. 18365
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals named "Ben" with their associated numerical identifiers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ben."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     difficulty
    -0.62
    hower
    -0.61
    inarily
    -0.59
    dayName
    -0.59
     Dialogue
    -0.58
    ngth
    -0.58
    ansk
    -0.57
     abundance
    -0.56
     Parables
    -0.56
    åŃ
    -0.56
    POSITIVE LOGITS
    jamin
    1.66
    nington
    1.24
    oit
    1.20
    imaru
    0.95
    ghazi
    0.94
    cher
    0.90
    chers
    0.88
    enson
    0.87
    ito
    0.87
    ning
    0.86
    Activations Density 0.025%

    No Known Activations