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. 8-RES-JB
    6. 3556
    Prev
    Next
    INDEX
    Explanations

    names related to the location "Odisha"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or character named "Od."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iard
    -0.86
    ancial
    -0.76
    staff
    -0.69
    baugh
    -0.68
    ++++++++++++++++
    -0.67
    agne
    -0.66
    boards
    -0.66
    ivities
    -0.65
    acters
    -0.65
     Chapman
    -0.65
    POSITIVE LOGITS
    yssey
    1.11
    landish
    0.81
    mega
    0.79
    cean
    0.77
    culus
    0.75
    toc
    0.74
    ceans
    0.74
    worldly
    0.72
    chemy
    0.72
    AMA
    0.71
    Activations Density 0.100%

    No Known Activations