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. 9-RES-JB
    6. 661
    Prev
    Next
    INDEX
    Explanations

    references to specific issues of magazines or publications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific magazine issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rophic
    -0.80
    sing
    -0.75
    raltar
    -0.75
    heed
    -0.74
    bones
    -0.71
     arom
    -0.68
    urally
    -0.68
    eric
    -0.67
    rous
    -0.66
    roo
    -0.64
    POSITIVE LOGITS
     Comics
    0.84
     thereof
    0.74
    rint
    0.71
    Issue
    0.70
     (#
    0.68
    Limited
    0.68
     reprint
    0.67
    Magazine
    0.67
    Reader
    0.67
     Contents
    0.67
    Activations Density 0.038%

    No Known Activations