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. 5242
    Prev
    Next
    INDEX
    Explanations

    specific entities and locations mentioned in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    common conjunctions and prepositions used in complex ideas or statements

    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
     EFF
    -0.79
     behav
    -0.78
     ����
    -0.75
     distingu
    -0.71
     SERVICE
    -0.71
     SAN
    -0.70
    assetsadobe
    -0.69
     toget
    -0.68
     ESP
    -0.67
     acknow
    -0.67
    POSITIVE LOGITS
    zon
    0.88
    gger
    0.88
    utenberg
    0.87
    winter
    0.87
    hardt
    0.86
    wig
    0.84
    inia
    0.83
    chid
    0.83
    raq
    0.83
    kin
    0.83
    Activations Density 0.282%

    No Known Activations