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. 7-RES-JB
    6. 14923
    Prev
    Next
    INDEX
    Explanations

    financial terms related to market performance, such as highs and lows

    oai_token-act-pair · gpt-3.5-turbo

    financial metrics related to record highs and lows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avering
    -0.73
    cipl
    -0.70
    onge
    -0.69
    argon
    -0.66
    oute
    -0.66
    athe
    -0.65
     parting
    -0.65
     rad
    -0.62
    itri
    -0.62
     parted
    -0.61
    POSITIVE LOGITS
     1929
    0.66
     inflation
    0.64
    bnb
    0.64
    Ĥİ
    0.64
    fters
    0.63
     landfall
    0.63
     Replay
    0.63
    riots
    0.63
    wcs
    0.62
     Holder
    0.62
    Activations Density 0.102%

    No Known Activations