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. 11-RES-JB
    6. 4609
    Prev
    Next
    INDEX
    Explanations

    references to things being taken off the market

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raped
    -0.76
    isson
    -0.73
    LOD
    -0.72
    ̶
    -0.67
    entimes
    -0.66
    handled
    -0.63
    DERR
    -0.63
    ousy
    -0.62
    CVE
    -0.61
    CEO
    -0.60
    POSITIVE LOGITS
     horizon
    1.36
     shelves
    1.18
     chopping
    1.10
     market
    1.09
     agenda
    1.06
     planet
    1.03
     table
    1.02
     streets
    0.97
     continent
    0.97
     shelf
    0.96
    Activations Density 0.110%

    No Known Activations