Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11878
    Prev
    Next
    INDEX
    Explanations

    references to the organization "Judicial Watch"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the organization "Judicial Watch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.76
     flavours
    -0.75
     fries
    -0.73
    wcs
    -0.68
    isable
    -0.67
     toast
    -0.67
    istic
    -0.65
     cure
    -0.65
    interstitial
    -0.65
     oxid
    -0.64
    POSITIVE LOGITS
    dog
    1.26
    tower
    1.17
    dogs
    1.16
     Watch
    0.95
    atcher
    0.84
     Dogs
    0.81
    andowski
    0.81
     Watching
    0.78
    point
    0.75
    wat
    0.74
    Activations Density 0.024%

    No Known Activations