Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 21975
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of segregated workspaces like "cubicles."

    oai_token-act-pair · gpt-3.5-turbo

    references to "cub" and variations of this term, indicating a focus on young animals, specifically cubs

    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
    ++++
    -0.88
    ++++++++++++++++
    -0.81
    wine
    -0.67
    #$#$
    -0.64
    +++
    -0.64
    IGN
    -0.62
    WAYS
    -0.60
    ++++++++
    -0.60
     autop
    -0.60
    ORTS
    -0.59
    POSITIVE LOGITS
    icle
    1.22
    icles
    1.13
    ility
    1.01
    bies
    0.97
    bage
    0.87
    ey
    0.85
    ensis
    0.85
    anqu
    0.85
    raph
    0.84
    ebook
    0.84
    Activations Density 0.087%

    No Known Activations