© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6-RES-JB
    11. 17091
    Prev
    Next
    INDEX
    Explanations

    numbers with dashes, colons, and units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    numerical values formatted as measurements or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abase
    -0.69
     Ridley
    -0.67
     Thumbnails
    -0.66
     Foss
    -0.63
     Masquerade
    -0.63
     Ashes
    -0.63
     Leia
    -0.56
    yles
    -0.56
    vier
    -0.55
     tert
    -0.55
    POSITIVE LOGITS
    999
    0.82
    acan
    0.76
    9999
    0.74
    090
    0.71
    dogs
    0.69
    576
    0.67
    unic
    0.66
    NPR
    0.66
    295
    0.65
    monary
    0.65
    Activations Density 0.127%

    No Known Activations