© 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. 10-RES-JB
    11. 6539
    Prev
    Next
    INDEX
    Explanations

    words related to making adjustments or variations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to making modifications or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gom
    -0.78
    NetMessage
    -0.77
    utra
    -0.75
    chu
    -0.72
    ijk
    -0.70
    irez
    -0.70
    ī
    -0.68
    ciating
    -0.67
    intel
    -0.67
    cade
    -0.67
    POSITIVE LOGITS
     accordingly
    1.02
     adjustments
    0.92
     adjusts
    0.87
     downwards
    0.87
    ments
    0.85
     adjusting
    0.84
     adjustment
    0.83
     downward
    0.80
     adjust
    0.80
     adjusted
    0.78
    Activations Density 0.037%

    No Known Activations