© 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. 1-RES-JB
    11. 12970
    Prev
    Next
    INDEX
    Explanations

    names or terms related to scooters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of scooters and individuals associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nant
    -0.82
    enc
    -0.71
    nants
    -0.64
    intent
    -0.63
    pressed
    -0.63
    press
    -0.63
     ILCS
    -0.62
    sent
    -0.60
    ends
    -0.60
     incentives
    -0.59
    POSITIVE LOGITS
    ooter
    1.54
    ooters
    1.10
    xon
    0.85
    hoe
    0.85
    zzi
    0.82
    ttes
    0.79
    erness
    0.77
    irtual
    0.77
    alore
    0.76
    hattan
    0.74
    Activations Density 0.003%

    No Known Activations