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. 3518
    Prev
    Next
    INDEX
    Explanations

    non-subscription related phrases such as "see," "try again later," and various other unrelated terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating error messages related to subscription or account access issues

    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
    geist
    -0.65
     grooming
    -0.60
     cult
    -0.60
     Mara
    -0.58
     Mog
    -0.57
     foremost
    -0.56
     Manson
    -0.56
     Uriel
    -0.55
    ©¶æ
    -0.55
     ["
    -0.54
    POSITIVE LOGITS
     Flavoring
    0.67
    ModLoader
    0.66
    qus
    0.64
    olesterol
    0.62
     nor
    0.61
    á½
    0.61
    OTS
    0.61
    Please
    0.60
    ickets
    0.60
    ername
    0.59
    Activations Density 0.036%

    No Known Activations