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. 10-RES-JB
    6. 22978
    Prev
    Next
    INDEX
    Explanations

    names with the pattern "St" followed by a number (e.g., St 10, St 9, St 8), which might indicate a specific individual or entity in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleas
    -0.62
     poster
    -0.61
     rip
    -0.60
     advertisements
    -0.60
     timely
    -0.59
     pods
    -0.58
     Chapters
    -0.58
     accessibility
    -0.58
     "$:/
    -0.58
     recommendations
    -0.58
    POSITIVE LOGITS
    oppable
    1.21
    okes
    1.19
    ahl
    1.18
    oller
    1.14
    alker
    1.13
    irling
    1.12
    olt
    1.10
    robe
    1.09
    onew
    1.09
    inson
    1.08
    Activations Density 0.018%

    No Known Activations