© 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. 8-RES-JB
    11. 743
    Prev
    Next
    INDEX
    Explanations

    file extensions related to music files

    oai_token-act-pair · gpt-3.5-turbo

    file extensions or technical terms related to multimedia formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Else
    -0.72
    mberg
    -0.71
    WAYS
    -0.67
    beit
    -0.66
    nces
    -0.65
    wal
    -0.64
    idad
    -0.62
     striking
    -0.62
     Leilan
    -0.62
     prevailing
    -0.61
    POSITIVE LOGITS
    ixels
    1.02
    hetamine
    1.01
    oleon
    1.00
    onent
    0.99
    olitan
    0.98
    EG
    0.93
    ierrez
    0.92
    alm
    0.92
    asus
    0.90
    ixel
    0.89
    Activations Density 0.035%

    No Known Activations