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. 8-RES-JB
    6. 20824
    Prev
    Next
    INDEX
    Explanations

    racial, political, and geographical contrasts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    united
    -0.74
    ortium
    -0.65
    mun
    -0.64
    shared
    -0.63
    Downloadha
    -0.61
     RELE
    -0.60
    Rocket
    -0.60
    afety
    -0.60
    hot
    -0.60
    xtap
    -0.60
    POSITIVE LOGITS
     ones
    1.71
     counterparts
    1.18
     counterpart
    1.05
     Ones
    1.04
     versions
    0.79
     equivalents
    0.73
     theirs
    0.72
     ours
    0.72
     sensibilities
    0.72
     brethren
    0.72
    Activations Density 0.476%

    No Known Activations