© 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. 9-RES-JB
    11. 13857
    Prev
    Next
    INDEX
    Explanations

    terms related to size, extent, or magnitude of different issues or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate magnitude or scale related to problems or issues

    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
    nis
    -0.75
    ade
    -0.75
    orthy
    -0.71
    center
    -0.71
    ools
    -0.71
    cellaneous
    -0.70
    eka
    -0.69
    nob
    -0.68
    ittee
    -0.67
     Cosponsors
    -0.66
    POSITIVE LOGITS
     hostilities
    0.99
     these
    0.93
     our
    0.84
     their
    0.83
     penetration
    0.82
     criminality
    0.81
     those
    0.80
     damage
    0.80
     disruption
    0.78
     devastation
    0.78
    Activations Density 0.133%

    No Known Activations