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. 4-RES-JB
    6. 5919
    Prev
    Next
    INDEX
    Explanations

    phrases or terms that are being "put forth" or presented for consideration or discussion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "put forth."

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

    No Comments

    Negative Logits
    cius
    -0.69
     Bulg
    -0.67
     abolished
    -0.65
     Cohen
    -0.64
    azo
    -0.64
     evict
    -0.63
    illard
    -0.63
    zzo
    -0.61
     rack
    -0.61
     Marble
    -0.60
    POSITIVE LOGITS
    right
    1.01
    comings
    0.96
    stand
    0.91
    forth
    0.88
    rus
    0.83
    cakes
    0.81
    ensibly
    0.79
    rance
    0.78
    urst
    0.78
    )=(
    0.77
    Activations Density 0.007%

    No Known Activations