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. 5617
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Gatlinburg"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Gat" in various contexts

    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
    interstitial
    -0.75
    ¥ŀ
    -0.68
    perse
    -0.67
    theless
    -0.65
     ancest
    -0.63
    pta
    -0.63
     tiss
    -0.60
    PRES
    -0.60
    vironment
    -0.60
    ĺħ
    -0.59
    POSITIVE LOGITS
    herer
    1.25
    estone
    1.03
    igue
    0.95
    lin
    0.92
    estones
    0.92
    rop
    0.91
    eless
    0.90
    glers
    0.90
    rill
    0.90
    itude
    0.89
    Activations Density 0.010%

    No Known Activations