© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 19440
    Prev
    Next
    INDEX
    Explanations

    statistical rankings or superlatives such as highest, lowest, most, and best in a given context

    oai_token-act-pair · gpt-3.5-turbo

    comparative statistics related to rankings and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unes
    -0.83
    ertain
    -0.70
    ribut
    -0.69
    tif
    -0.69
    ¯¯¯¯¯¯¯¯
    -0.67
    dd
    -0.65
     Matters
    -0.65
    prison
    -0.65
    must
    -0.64
    ãĥij
    -0.62
    POSITIVE LOGITS
     overall
    0.78
     amount
    0.75
     firepower
    0.73
     record
    0.73
     bang
    0.71
     turnaround
    0.71
     mileage
    0.71
     ever
    0.69
     latitude
    0.69
     breakdown
    0.69
    Activations Density 0.102%

    No Known Activations