© 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. 7-RES-JB
    11. 1893
    Prev
    Next
    INDEX
    Explanations

    text related to reports, news, and announcements

    oai_token-act-pair · gpt-3.5-turbo

    formal or official statements and reports, particularly those pertaining to legal or authoritative matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zion
    -0.61
    proc
    -0.58
     Entered
    -0.57
     Sovere
    -0.56
    ãĤ¯
    -0.55
     favourable
    -0.54
     colonization
    -0.54
     coh
    -0.54
    Cor
    -0.53
    fac
    -0.53
    POSITIVE LOGITS
     also
    0.76
     additionally
    0.75
     furthermore
    0.68
     ALSO
    0.66
    urai
    0.65
    llah
    0.64
    ohm
    0.64
     smelled
    0.63
     fixme
    0.62
    DragonMagazine
    0.62
    Activations Density 0.908%

    No Known Activations