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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    6. 2304
    Prev
    Next
    INDEX
    Explanations

    percentages or proportions

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical percentages, particularly regarding demographics and occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ires
    -0.66
    su
    -0.63
     Join
    -0.62
    arr
    -0.60
    dev
    -0.59
    eng
    -0.59
     unimagin
    -0.59
    ink
    -0.58
    uel
    -0.58
    opian
    -0.58
    POSITIVE LOGITS
     percentage
    3.60
     percentages
    2.59
     Percentage
    2.46
     proportion
    1.95
    percent
    1.94
    Percent
    1.65
     %
    1.62
     percent
    1.61
     ratio
    1.57
     Percent
    1.47
    Activations Density 0.012%

    No Known Activations