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. 7-RES-JB
    6. 13098
    Prev
    Next
    INDEX
    Explanations

    links or URLs

    oai_token-act-pair · gpt-3.5-turbo

    short domain names or web-related identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     refres
    -0.74
     Caption
    -0.61
    accompan
    -0.61
     Jungle
    -0.58
     Democracy
    -0.58
     sleeping
    -0.57
     sunrise
    -0.57
     ages
    -0.57
     disappearing
    -0.56
     retaining
    -0.56
    POSITIVE LOGITS
    cdn
    0.95
    #$
    0.88
    igslist
    0.87
    vey
    0.77
    noon
    0.77
    domain
    0.76
    tm
    0.75
    ovy
    0.74
    jc
    0.74
    arcity
    0.72
    Activations Density 0.111%

    No Known Activations