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. 215
    Prev
    Next
    INDEX
    Explanations

    words or phrases that use accents like "ó" and "án"

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific locations or identifiers in a context

    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
    orial
    -0.75
    uality
    -0.73
    pread
    -0.71
     CST
    -0.69
    achine
    -0.69
    orship
    -0.66
    idences
    -0.66
    ovie
    -0.65
    acle
    -0.64
    riott
    -0.64
    POSITIVE LOGITS
    rien
    1.07
    atl
    0.88
    ÃįÃį
    0.86
    ··
    0.85
    rio
    0.83
    ng
    0.83
    ð
    0.83
    vernment
    0.80
    sand
    0.79
    s
    0.78
    Activations Density 0.031%

    No Known Activations