© 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. 8-RES-JB
    11. 21755
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal processes or systematic approaches

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes or evaluations conducted on a case-by-case basis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mosp
    -0.78
    dor
    -0.78
    imar
    -0.78
    wi
    -0.77
    erville
    -0.75
    asa
    -0.75
    paces
    -0.74
    ceived
    -0.74
    soType
    -0.74
    jon
    -0.73
    POSITIVE LOGITS
     instructions
    0.88
     rundown
    0.87
     basis
    0.86
     comparisons
    0.82
     breakdown
    0.82
     guide
    0.77
     correspondence
    0.76
     outline
    0.74
     catalog
    0.71
     catalogue
    0.71
    Activations Density 0.051%

    No Known Activations