© 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. 9-RES-JB
    11. 2992
    Prev
    Next
    INDEX
    Explanations

    words related to sequences or events that are expected to happen in the future

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes and events leading up to significant actions or milestones

    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
    <?
    -0.82
    ccording
    -0.67
    ãĥ³ãĤ¸
    -0.67
     FAR
    -0.62
     anecd
    -0.62
    oir
    -0.61
     Cosponsors
    -0.61
    behind
    -0.61
    wrong
    -0.60
     paraph
    -0.60
    POSITIVE LOGITS
     deadline
    1.06
     cutoff
    0.97
     arrival
    0.87
     arrives
    0.85
     begins
    0.84
     onset
    0.84
     dawn
    0.80
     expires
    0.78
    aturday
    0.77
    pection
    0.77
    Activations Density 0.265%

    No Known Activations