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. 11-RES-JB
    6. 3952
    Prev
    Next
    INDEX
    Explanations

    references to a specific TV show titled "Meet the Press."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific television programs and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.61
     strand
    -0.60
     lesson
    -0.58
    itone
    -0.58
     Grad
    -0.56
     Tide
    -0.56
    teen
    -0.54
    rency
    -0.54
     Cinderella
    -0.54
     trickle
    -0.53
    POSITIVE LOGITS
    apor
    0.85
    ulkan
    0.74
    adr
    0.69
    packages
    0.68
    bug
    0.66
    helm
    0.66
    ãĤ¡
    0.66
    BUG
    0.66
    urg
    0.65
    lyak
    0.65
    Activations Density 0.124%

    No Known Activations