© 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. 18206
    Prev
    Next
    INDEX
    Explanations

    percentages or related numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to percentages or statistical certainty

    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
    worldly
    -0.89
    zie
    -0.85
    sels
    -0.72
    åĤ
    -0.72
    hap
    -0.69
    ipples
    -0.68
    */(
    -0.67
    EStream
    -0.67
    isure
    -0.67
     Skies
    -0.66
    POSITIVE LOGITS
     Invisible
    0.79
     certainty
    0.77
    heartedly
    0.73
     ethanol
    0.72
     pure
    0.70
     accurate
    0.69
     satisfaction
    0.68
     humidity
    0.66
     True
    0.64
     assured
    0.64
    Activations Density 0.048%

    No Known Activations