© 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. 16617
    Prev
    Next
    INDEX
    Explanations

    adjectives related to personal characteristics or qualities

    oai_token-act-pair · gpt-3.5-turbo

    present tense and past tense forms of the verb "to be."

    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
    anos
    -0.66
     Inqu
    -0.56
    raltar
    -0.55
    pheus
    -0.54
    zan
    -0.53
    iken
    -0.52
     inquiries
    -0.51
    ERY
    -0.51
     scraps
    -0.51
    INC
    -0.50
    POSITIVE LOGITS
     compared
    0.91
     relative
    0.78
    Interstitial
    0.78
     supposed
    0.73
    .
    0.72
     nowadays
    0.69
     regarding
    0.69
    !.
    0.69
     unto
    0.67
     against
    0.67
    Activations Density 0.091%

    No Known Activations