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. 10819
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that something is not related or relevant to a particular topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases asserting the irrelevance or disconnection of topics

    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
    ©¶æ¥µ
    -0.84
    umerous
    -0.78
    earchers
    -0.77
    aughters
    -0.75
    estyles
    -0.72
    endiary
    -0.71
    enza
    -0.70
     teasp
    -0.70
    sites
    -0.70
    ccording
    -0.70
    POSITIVE LOGITS
     ours
    1.34
     yours
    1.31
     us
    1.27
     reality
    1.27
     me
    1.19
     theirs
    1.18
     humanity
    1.16
     itself
    1.09
     feminism
    1.02
     hers
    1.00
    Activations Density 0.336%

    No Known Activations