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. 9-RES-JB
    6. 6622
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaborative efforts or actions involving multiple parties

    oai_token-act-pair · gpt-3.5-turbo
    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
    ilk
    -0.79
    ylon
    -0.67
    acha
    -0.66
    aghetti
    -0.65
    worms
    -0.64
    acious
    -0.64
    ongs
    -0.63
    cale
    -0.62
    dylib
    -0.62
    uve
    -0.62
    POSITIVE LOGITS
     venture
    1.00
     ventures
    0.91
     chiefs
    0.81
     declaration
    0.76
     effort
    0.75
     resolution
    0.73
    ness
    0.70
    iliation
    0.70
     fundraising
    0.69
     Venture
    0.68
    Activations Density 0.031%

    No Known Activations