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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 15742
    Prev
    Next
    INDEX
    Explanations

    names containing the root "sson."

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of names ending with "sson"

    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
    ãĥ£
    -0.68
     Pax
    -0.65
     Sussex
    -0.61
    payers
    -0.60
    ================
    -0.59
     fet
    -0.59
     Blitz
    -0.58
     vig
    -0.58
    POS
    -0.57
     utmost
    -0.55
    POSITIVE LOGITS
    sson
    1.25
    ð
    0.90
    sky
    0.85
    nir
    0.85
    å
    0.85
    ensen
    0.82
    ansson
    0.81
    gren
    0.80
    qv
    0.79
    lund
    0.79
    Activations Density 0.017%

    No Known Activations