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. 9-RES-JB
    6. 6395
    Prev
    Next
    INDEX
    Explanations

    adjectives describing something as beneficial, practical, or advantageous

    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
    otta
    -0.65
     boarded
    -0.65
    uph
    -0.64
     Alive
    -0.62
    agate
    -0.61
    buck
    -0.61
     Bom
    -0.60
     Pall
    -0.59
     Kard
    -0.59
    olition
    -0.58
    POSITIVE LOGITS
     idiots
    1.16
     adjunct
    0.83
     insights
    0.81
     tools
    0.80
    tip
    0.80
     insight
    0.78
    fully
    0.78
     tool
    0.76
    tips
    0.75
    iences
    0.72
    Activations Density 0.048%

    No Known Activations