© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 9845
    Prev
    Next
    INDEX
    Explanations

    financial and statistical information, such as revenues, production rates, and employee numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to business metrics and transactions

    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
    .]
    -0.60
    >[
    -0.60
     intervening
    -0.57
    weak
    -0.57
    gap
    -0.57
    another
    -0.56
    appro
    -0.55
    aban
    -0.55
    ?]
    -0.55
     Again
    -0.54
    POSITIVE LOGITS
     regularly
    0.89
     tours
    0.88
     nightly
    0.79
     weddings
    0.79
     concerts
    0.78
     exhibitions
    0.77
     annually
    0.75
     frequently
    0.74
     mainly
    0.73
     routinely
    0.72
    Activations Density 1.023%

    No Known Activations