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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 9783
    Prev
    Next
    INDEX
    Explanations

    points, drawbacks, concessions, advantages, ups, caveats, features, themes, issues, insights, limitations, and results

    oai_token-act-pair · gpt-3.5-turbo

    references to key points, advantages, and challenges in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.79
     Tsukuyomi
    -0.66
    ļéĨĴ
    -0.63
    psc
    -0.61
    raid
    -0.60
    definition
    -0.60
     Alone
    -0.60
    heid
    -0.59
     TAMADRA
    -0.57
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.57
    POSITIVE LOGITS
     pertaining
    1.05
     relating
    0.96
     besides
    0.92
     regarding
    0.90
     related
    0.89
     sprinkled
    0.82
    hooting
    0.82
    ensical
    0.82
     concerning
    0.81
     including
    0.81
    Activations Density 0.293%

    No Known Activations