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. 2-RES-JB
    6. 8675
    Prev
    Next
    INDEX
    Explanations

    locations or keywords related to the town of "Eureka."

    oai_token-act-pair · gpt-3.5-turbo

    references to subsidies and related financial themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fracture
    -0.72
     Bride
    -0.71
     Tie
    -0.70
     Cong
    -0.69
     Hole
    -0.68
     Typhoon
    -0.65
     Figure
    -0.64
     Table
    -0.63
     fractures
    -0.63
    hole
    -0.63
    POSITIVE LOGITS
    iaries
    1.12
    iary
    1.11
    ifully
    1.08
    otine
    1.01
    iful
    0.97
    anium
    0.96
    roid
    0.93
    aceous
    0.92
    opol
    0.92
    ende
    0.91
    Activations Density 0.018%

    No Known Activations