© 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 EvalsExportsinterp-engineNEWAPI 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. 7150
    Prev
    Next
    INDEX
    Explanations

    computer-related terms, specifically related to files, data, and programming

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific nouns or terms related to various categories, such as objects or actions

    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
    awar
    -0.70
    URA
    -0.68
    Balt
    -0.61
    umm
    -0.61
    ivas
    -0.61
    UCT
    -0.60
     Bulg
    -0.56
    ACA
    -0.56
    NA
    -0.56
    oult
    -0.56
    POSITIVE LOGITS
    theless
    1.04
    tenance
    0.77
    istan
    0.74
    DragonMagazine
    0.71
    âĦ¢
    0.68
    fter
    0.68
    DX
    0.67
     wip
    0.66
    erences
    0.65
    ®
    0.65
    Activations Density 0.390%

    No Known Activations