© 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. 9935
    Prev
    Next
    INDEX
    Explanations

    phrases related to minor league baseball

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Triple" in relation to sports or competitions

    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
    istry
    -0.79
    heit
    -0.71
    ears
    -0.69
    earing
    -0.69
    atar
    -0.68
    sbm
    -0.68
    agher
    -0.68
    netflix
    -0.65
    enegger
    -0.65
    papers
    -0.64
    POSITIVE LOGITS
    plets
    0.99
    plet
    0.99
    ty
    0.94
    reme
    0.83
    ts
    0.81
    ple
    0.81
     digits
    0.77
    leans
    0.73
    toe
    0.71
    teen
    0.71
    Activations Density 0.034%

    No Known Activations