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. 8-RES-JB
    6. 16301
    Prev
    Next
    INDEX
    Explanations

    phrases relating to presenting two options or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases questioning the existence of a situation or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pony
    -0.66
     Summit
    -0.59
     Trophy
    -0.59
     Room
    -0.56
     Tele
    -0.55
     Toad
    -0.54
     Tec
    -0.54
     Scrib
    -0.53
     Symphony
    -0.53
     Bron
    -0.52
    POSITIVE LOGITS
    acles
    0.96
    Else
    0.94
    acle
    0.90
    nam
    0.79
    rogens
    0.71
     else
    0.68
    ivably
    0.66
    acl
    0.65
    pheus
    0.63
    abouts
    0.61
    Activations Density 0.019%

    No Known Activations