© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 16402
    Prev
    Next
    INDEX
    Explanations

    common themes related to sports events or games

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "opener" in the context of sports events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iable
    -0.66
    nda
    -0.65
    ivan
    -0.63
     Hume
    -0.63
    remlin
    -0.63
    lements
    -0.62
    endi
    -0.62
    iva
    -0.62
    Memory
    -0.62
    ancies
    -0.62
    POSITIVE LOGITS
     opener
    1.57
    glers
    1.06
    spection
    0.86
    daq
    0.86
     externalToEVAOnly
    0.80
     opens
    0.78
     showc
    0.76
    uberty
    0.76
    terson
    0.71
     prol
    0.71
    Activations Density 0.005%

    No Known Activations