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. 9805
    Prev
    Next
    INDEX
    Explanations

    items or lists in a sentence marked by the presence of "etc"

    oai_token-act-pair · gpt-3.5-turbo

    references to lists or items in various formats

    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
     Divinity
    -0.69
     Moor
    -0.67
    deep
    -0.64
     eye
    -0.63
     Liqu
    -0.63
     CPR
    -0.62
     Spirit
    -0.61
     flirt
    -0.60
     holidays
    -0.60
     Lav
    -0.60
    POSITIVE LOGITS
    ÃĥÃĤÃĥÃĤ
    1.12
    ÃĥÃĤ
    1.09
    %),
    1.01
    %,
    1.00
    %).
    0.99
    %)
    0.99
    .):
    0.98
    .,
    0.98
    %-
    0.94
    ĸļ士
    0.93
    Activations Density 0.145%

    No Known Activations