© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 404
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the uniqueness or importance of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating a comparison of quantity or importance, typically emphasizing "no less" than a certain amount

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

    No Comments

    Negative Logits
    ãĤ±
    -0.69
     Translation
    -0.68
    Ö¼
    -0.67
    okin
    -0.66
    Sys
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.64
     Nevada
    -0.64
     Ball
    -0.63
     Net
    -0.63
     Scale
    -0.63
    POSITIVE LOGITS
     than
    0.89
    etheless
    0.79
    aneously
    0.75
    nces
    0.73
    ened
    0.73
    aciously
    0.69
     behaved
    0.68
    oubted
    0.68
    iating
    0.68
     fortunate
    0.68
    Activations Density 0.015%

    No Known Activations