© 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. 4145
    Prev
    Next
    INDEX
    Explanations

    quantities or numbers preceded by words like "several," "few," "couple," "handful," or "two."

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or numerical descriptors, particularly small amounts

    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
    Reviewer
    -0.70
    tick
    -0.69
    ask
    -0.69
    illet
    -0.66
    saw
    -0.64
     Profile
    -0.64
    urden
    -0.63
    imester
    -0.62
    Led
    -0.62
    ESE
    -0.61
    POSITIVE LOGITS
     others
    1.43
     other
    1.25
    other
    0.93
     accompanying
    0.91
     else
    0.89
     Others
    0.88
     additional
    0.87
     importantly
    0.85
     subsequent
    0.84
     assorted
    0.83
    Activations Density 0.231%

    No Known Activations