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. 13806
    Prev
    Next
    INDEX
    Explanations

    dates or years in the context of events or product releases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "debuted" and related concepts of introductions or premieres

    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
    pler
    -0.90
    illion
    -0.84
    pled
    -0.81
    ilion
    -0.77
    acks
    -0.76
    acking
    -0.72
    eding
    -0.72
    ning
    -0.70
    ources
    -0.68
    etary
    -0.67
    POSITIVE LOGITS
    Reviewer
    0.91
    nesday
    0.84
    glers
    0.84
     Democr
    0.82
    æ©
    0.81
    ————
    0.76
    timer
    0.75
    0000000
    0.75
    ternity
    0.74
    yrs
    0.74
    Activations Density 0.024%

    No Known Activations