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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4136
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific date and time events

    oai_token-act-pair · gpt-3.5-turbo

    instances of empty or placeholder text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.66
    edIn
    -0.64
    omething
    -0.60
    ????????
    -0.60
    selves
    -0.60
    200000
    -0.60
    ean
    -0.59
    nings
    -0.59
    minster
    -0.58
    esides
    -0.57
    POSITIVE LOGITS
     Flickr
    0.86
     behalf
    0.82
     Aging
    0.79
     Tue
    0.78
    click
    0.78
    topic
    0.75
     Blog
    0.74
    LIN
    0.72
    LINE
    0.71
     Manga
    0.70
    Activations Density 0.042%

    No Known Activations