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. 6-RES-JB
    6. 4521
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific media outlet and offers related to it

    oai_token-act-pair · gpt-3.5-turbo

    references to specific publications and their content offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lda
    -0.78
    âĢİ
    -0.78
    lain
    -0.73
    aimon
    -0.73
    urized
    -0.70
    ivas
    -0.70
    ibaba
    -0.70
    llan
    -0.68
    saf
    -0.68
    uably
    -0.67
    POSITIVE LOGITS
     Literary
    0.76
     content
    0.74
    entimes
    0.74
     occasional
    0.73
     strives
    0.70
    Ble
    0.69
     Content
    0.66
     subscribing
    0.66
     trave
    0.63
     deadline
    0.62
    Activations Density 0.057%

    No Known Activations