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. 0-RES-JB
    6. 24448
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "detailed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lymp
    -0.77
    <?
    -0.70
    mania
    -0.70
     oppress
    -0.67
    (-
    -0.67
    mouth
    -0.66
    ardless
    -0.64
    boy
    -0.63
    marg
    -0.63
    advertising
    -0.62
    POSITIVE LOGITS
     detailed
    3.45
     detail
    1.88
    Detailed
    1.77
     details
    1.77
     precise
    1.45
     outlined
    1.45
     exhaustive
    1.45
     comprehensive
    1.43
     meticulous
    1.40
     detailing
    1.33
    Activations Density 0.014%

    No Known Activations