© 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. 9-RES-JB
    11. 15818
    Prev
    Next
    INDEX
    Explanations

    keywords related to signs, clues, and evidence

    oai_token-act-pair · gpt-3.5-turbo

    indicators of change or signs in a situation

    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
    ourses
    -0.75
     concurrently
    -0.69
    ommod
    -0.69
     federation
    -0.68
    OVA
    -0.67
    Ranked
    -0.66
    HQ
    -0.65
    quad
    -0.64
    Private
    -0.64
    eneg
    -0.64
    POSITIVE LOGITS
     clues
    1.06
     Signs
    0.92
     hint
    0.90
     clue
    0.87
     indicating
    0.86
     pointing
    0.83
     ticking
    0.83
    eele
    0.83
     unmist
    0.83
     marker
    0.82
    Activations Density 0.676%

    No Known Activations