© 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. 1757
    Prev
    Next
    INDEX
    Explanations

    terms related to metadata

    oai_token-act-pair · gpt-3.5-turbo

    references to meta-analysis and metadata

    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
    shire
    -0.83
    iens
    -0.82
    Interstitial
    -0.77
    ivity
    -0.75
    owship
    -0.74
    ESCO
    -0.69
     Franks
    -0.68
     Petty
    -0.67
     Vend
    -0.67
    icular
    -0.67
    POSITIVE LOGITS
    plot
    1.07
    ethical
    0.94
    alyses
    0.93
    verse
    0.92
    ographically
    0.81
     guiActiveUn
    0.78
    allo
    0.77
    enter
    0.75
    ethyl
    0.75
    hei
    0.75
    Activations Density 0.022%

    No Known Activations