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. 6631
    Prev
    Next
    INDEX
    Explanations

    phrases related to a wide variety or diverse selection of items

    oai_token-act-pair · gpt-3.5-turbo

    references to a variety of topics or options

    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
    ©¶æ
    -0.78
     Cust
    -0.74
     Dull
    -0.71
    slow
    -0.68
     Keeper
    -0.66
     Dominion
    -0.64
     Brief
    -0.64
     Steal
    -0.63
    Slow
    -0.62
     Ital
    -0.62
    POSITIVE LOGITS
    ortment
    0.88
    oway
    0.74
    channelAvailability
    0.73
    iability
    0.70
     (>
    0.70
    ietal
    0.69
     opinions
    0.68
     viewpoints
    0.67
     imaginable
    0.66
     ranging
    0.66
    Activations Density 0.068%

    No Known Activations