© 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. 8924
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "CB" followed by a number (e.g., CB 10, CB 9, CB 8), potentially related to specific entities or topics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "CBP", likely related to border control or security contexts

    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
    wine
    -0.75
    lihood
    -0.72
    aciously
    -0.68
    imity
    -0.68
    zzo
    -0.67
    falls
    -0.67
     Gors
    -0.67
    umerable
    -0.64
    ufact
    -0.63
    velt
    -0.62
    POSITIVE LOGITS
    erning
    0.75
    aret
    0.75
    SEA
    0.74
    dar
    0.74
    RL
    0.73
    QB
    0.71
    annon
    0.71
    oard
    0.71
    anut
    0.70
    STAR
    0.70
    Activations Density 0.045%

    No Known Activations