© 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. 8602
    Prev
    Next
    INDEX
    Explanations

    percentages or proportions mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    references to percentages

    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
     Supplemental
    -0.74
     KC
    -0.72
    HCR
    -0.68
     Kap
    -0.64
     Shame
    -0.63
     KH
    -0.63
    ITED
    -0.63
    çīĪ
    -0.62
     ABE
    -0.61
     Ku
    -0.60
    POSITIVE LOGITS
    age
    1.28
    percent
    1.28
    ages
    1.05
    enger
    0.99
    Percent
    0.99
    renheit
    0.98
    imeter
    0.94
    imet
    0.93
    imeters
    0.93
    ername
    0.92
    Activations Density 0.015%

    No Known Activations