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. 21206
    Prev
    Next
    INDEX
    Explanations

    terms related to business deals and transactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to business transactions and customization

    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
     reper
    -0.68
    NetMessage
    -0.68
     Haram
    -0.65
    hered
    -0.65
     Scotia
    -0.63
    channelAvailability
    -0.61
    combe
    -0.61
     constitu
    -0.58
     penn
    -0.58
    EGA
    -0.57
    POSITIVE LOGITS
    ers
    2.54
    er
    2.47
    ership
    2.17
    erate
    1.48
    ER
    1.45
    ering
    1.44
    ered
    1.41
    ERS
    1.38
    erness
    1.35
    erd
    1.31
    Activations Density 0.217%

    No Known Activations