© 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. 8-RES-JB
    11. 17668
    Prev
    Next
    INDEX
    Explanations

    MLB-related terms, such as "ML" and "Major League Baseball"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "ML" or related acronyms, particularly in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forcing
    -0.73
    liest
    -0.66
    staking
    -0.64
     Rear
    -0.62
    fully
    -0.62
    ricular
    -0.61
    til
    -0.59
     Gamble
    -0.59
    lished
    -0.58
    hered
    -0.58
    POSITIVE LOGITS
    endon
    0.88
    ML
    0.87
    iquid
    0.85
    anguage
    0.85
    NP
    0.84
    TON
    0.84
    onge
    0.83
    TP
    0.83
    DN
    0.83
    arge
    0.83
    Activations Density 0.030%

    No Known Activations