Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 23084
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and verification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to verification and authority in information

    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
     awa
    -0.64
     tiss
    -0.53
     nodd
    -0.50
     Ivory
    -0.50
    apest
    -0.48
    nesday
    -0.47
    neau
    -0.47
    bestos
    -0.47
     concess
    -0.46
     showc
    -0.46
    POSITIVE LOGITS
    )?
    0.91
    ,[
    0.81
     ):
    0.69
    )
    0.69
    ),
    0.67
    ).
    0.67
    ).[
    0.65
    )[
    0.64
    ,)
    0.63
     (),
    0.62
    Activations Density 1.467%

    No Known Activations