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. 2-RES-JB
    6. 19090
    Prev
    Next
    INDEX
    Explanations

    mentions of cuts or reductions in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cuts."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agher
    -0.67
     cogn
    -0.67
     foam
    -0.66
    esthetic
    -0.63
     sediment
    -0.62
     planetary
    -0.61
    cells
    -0.60
     proportions
    -0.60
    ebook
    -0.60
     simulations
    -0.58
    POSITIVE LOGITS
    uts
    1.12
    atis
    1.00
    cheon
    0.93
    ileaks
    0.89
    ilitarian
    0.88
    atoes
    0.87
    opian
    0.84
    ierrez
    0.84
    kin
    0.84
    ument
    0.84
    Activations Density 0.006%

    No Known Activations