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. 22890
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a full stop and with a high amount of certainty or decisiveness

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express uncertainty or questions about understanding and social dynamics

    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
     upgr
    -0.73
     unden
    -0.72
     landfall
    -0.68
     panc
    -0.68
     mammoth
    -0.68
    ernaut
    -0.68
     exclusively
    -0.68
     sequential
    -0.68
     untouched
    -0.67
     sustained
    -0.66
    POSITIVE LOGITS
     Especially
    1.20
     Usually
    1.17
     Regardless
    1.17
     They
    1.17
     Often
    1.15
     Their
    1.15
     Particularly
    1.13
     Examples
    1.12
     Flavoring
    1.11
     Whether
    1.10
    Activations Density 0.750%

    No Known Activations