© 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. 7009
    Prev
    Next
    INDEX
    Explanations

    phrases related to shared spaces or resources

    oai_token-act-pair · gpt-3.5-turbo

    key concepts and terminology related to food, authority, and organizational structures

    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
    cale
    -0.86
    creen
    -0.78
    rower
    -0.75
    outhern
    -0.70
     redistributed
    -0.69
    ervative
    -0.68
    ensor
    -0.68
    etter
    -0.64
    ategory
    -0.64
    hetto
    -0.64
    POSITIVE LOGITS
    lets
    1.26
    ologies
    1.24
    ings
    1.21
    ages
    1.16
    cases
    1.12
    isations
    1.02
    backs
    1.01
    aments
    1.00
    naires
    0.98
    ments
    0.98
    Activations Density 0.877%

    No Known Activations