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. 0-RES-JB
    6. 2987
    Prev
    Next
    INDEX
    Explanations

    keywords related to optics and optical devices

    oai_token-act-pair · gpt-3.5-turbo

    references to specific brands or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raq
    -0.91
     Frieza
    -0.88
    ittle
    -0.74
    Lay
    -0.72
     sweeps
    -0.69
    hattan
    -0.69
    ammy
    -0.68
     disarm
    -0.67
    akura
    -0.67
    ollah
    -0.67
    POSITIVE LOGITS
     Opt
    3.42
     Arg
    2.07
    Opt
    1.94
    Arg
    1.47
     Geographic
    1.25
     OPT
    1.21
     optics
    1.19
     optic
    1.19
     Argon
    1.08
     Ips
    1.00
    Activations Density 0.039%

    No Known Activations