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. 3301
    Prev
    Next
    INDEX
    Explanations

    mentions of specific dates or time periods

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain punctuations, specifically periods

    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
    boro
    -0.86
    ĸļ
    -0.82
    kees
    -0.74
    utical
    -0.72
     purs
    -0.65
     wardrobe
    -0.63
     vocals
    -0.63
    atown
    -0.62
    utics
    -0.62
    ocobo
    -0.61
    POSITIVE LOGITS
    ccording
    1.13
    Meanwhile
    1.02
    Foreign
    0.92
    Asked
    0.92
    Analysis
    0.91
    AFP
    0.89
    Reporting
    0.88
    Prime
    0.86
    Fighting
    0.86
    Such
    0.86
    Activations Density 0.726%

    No Known Activations