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. 10-RES-JB
    6. 23804
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance or inevitability of a concept or event

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of "matter" or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aughters
    -0.69
    ç¥ŀ
    -0.68
    ©¶æ
    -0.67
    ãĤ®
    -0.66
    rones
    -0.66
    opter
    -0.65
    elta
    -0.63
    ovi
    -0.62
    seys
    -0.62
    obin
    -0.61
    POSITIVE LOGITS
     of
    0.94
    weight
    0.72
     quantity
    0.67
    bra
    0.65
    rance
    0.64
    atical
    0.62
     OF
    0.60
    ional
    0.60
    iful
    0.60
    utation
    0.59
    Activations Density 0.053%

    No Known Activations