Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 9921
    Prev
    Next
    INDEX
    Explanations

    verbs indicating demonstration or exhibition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "show."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.93
     srf
    -0.72
    tymology
    -0.71
    iche
    -0.70
     retaining
    -0.70
    ascus
    -0.70
    quartered
    -0.69
    theless
    -0.68
     compounded
    -0.68
     inhabited
    -0.68
    POSITIVE LOGITS
    biz
    0.95
    runners
    0.94
    manship
    0.92
    shows
    0.87
    ered
    0.87
    runner
    0.87
    alter
    0.84
    Hide
    0.79
    imony
    0.78
     Shows
    0.76
    Activations Density 0.061%

    No Known Activations