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. 6-RES-JB
    6. 9111
    Prev
    Next
    INDEX
    Explanations

    discussions related to policies, decisions, and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to sports and competitive events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.83
    Known
    -0.70
    Additional
    -0.68
    skip
    -0.66
    Refer
    -0.61
    Split
    -0.61
    Lower
    -0.60
    Available
    -0.58
    Similar
    -0.57
    pri
    -0.57
    POSITIVE LOGITS
     nob
    0.75
    !!!!!!!!
    0.67
    !"
    0.66
    eday
    0.64
    !'
    0.63
     everywhere
    0.62
     stupid
    0.62
    !'"
    0.60
     everybody
    0.59
     wherever
    0.59
    Activations Density 1.007%

    No Known Activations