© 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. 11-RES-JB
    11. 7447
    Prev
    Next
    INDEX
    Explanations

    phrases related to improving skills or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "up" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Anne
    -0.64
    oth
    -0.61
    mes
    -0.60
    ¯¯¯¯
    -0.60
    Closure
    -0.59
    ow
    -0.59
    Eye
    -0.58
    lean
    -0.58
    mouth
    -0.57
    BIT
    -0.57
    POSITIVE LOGITS
    river
    0.86
    hol
    0.80
    dates
    0.79
    raised
    0.77
     shop
    0.76
    grades
    0.74
    grading
    0.73
     nicely
    0.71
    dating
    0.68
    votes
    0.67
    Activations Density 0.136%

    No Known Activations