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. 9-RES-JB
    6. 12866
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific term ("Hyatt")

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific placeholders or tags in a structured document format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IFIED
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.72
    DERR
    -0.70
    Ø©
    -0.67
    emouth
    -0.66
    女
    -0.66
    Adds
    -0.65
    س
    -0.61
    ãĤ´ãĥ³
    -0.61
    iants
    -0.60
    POSITIVE LOGITS
    brid
    1.21
    brids
    1.20
    giene
    1.18
    undai
    1.10
    annis
    1.06
    rule
    1.05
    atts
    1.00
    bris
    0.92
    ster
    0.86
    tro
    0.86
    Activations Density 0.032%

    No Known Activations