© 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. 0-RES-JB
    11. 16391
    Prev
    Next
    INDEX
    Explanations

    numerical references to extremely large quantities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isf
    -0.73
    Conf
    -0.68
    inder
    -0.67
     Clinic
    -0.65
    inem
    -0.65
    etic
    -0.63
    ather
    -0.62
    Lee
    -0.60
     Condition
    -0.59
    acey
    -0.59
    POSITIVE LOGITS
     billions
    3.87
     trillions
    3.37
     millions
    2.73
     Millions
    2.01
     thousands
    1.98
     tens
    1.93
     billion
    1.89
    billion
    1.84
    illions
    1.78
     trillion
    1.76
    Activations Density 0.007%

    No Known Activations