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. 3-RES-JB
    6. 7667
    Prev
    Next
    INDEX
    Explanations

    quotations ending in a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pill
    -0.68
     starved
    -0.68
    gren
    -0.67
     purse
    -0.67
     reven
    -0.66
     refreshed
    -0.66
    packed
    -0.64
    ilion
    -0.62
     lifes
    -0.61
     uncond
    -0.61
    POSITIVE LOGITS
     Asked
    0.90
     Adds
    0.83
     Such
    0.82
     Ultimately
    0.80
     Needless
    0.80
     Those
    0.80
     Worse
    0.78
     Refer
    0.78
     According
    0.78
     Symptoms
    0.76
    Activations Density 0.097%

    No Known Activations