© 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. 2-RES-JB
    11. 23453
    Prev
    Next
    INDEX
    Explanations

    numerical values or words related to numerical concepts

    oai_token-act-pair · gpt-3.5-turbo

    numerical references and their contextual usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REAM
    -0.83
    loo
    -0.83
    hips
    -0.74
    ffee
    -0.70
    WARD
    -0.68
     Passage
    -0.67
    roud
    -0.67
    Accessory
    -0.63
    draft
    -0.62
    sein
    -0.61
    POSITIVE LOGITS
     num
    0.96
    emonic
    0.95
    eral
    0.91
    num
    0.90
    pty
    0.85
    iatures
    0.84
     Num
    0.83
    quist
    0.80
    ming
    0.80
    stress
    0.79
    Activations Density 0.009%

    No Known Activations