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. 8-RES-JB
    6. 3603
    Prev
    Next
    INDEX
    Explanations

    terms related to political and social issues, including global conflicts and human rights

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social and political issues, particularly those concerning various groups, movements, and legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    yss
    -0.72
    oret
    -0.68
     towed
    -0.63
    ulative
    -0.63
     Cheong
    -0.62
    chy
    -0.58
    huge
    -0.58
     snippet
    -0.57
     pend
    -0.57
    untled
    -0.57
    POSITIVE LOGITS
    casters
    0.90
    guards
    0.85
    ographies
    0.83
     alike
    0.83
    lance
    0.82
    outs
    0.82
    maps
    0.82
    casts
    0.81
    brids
    0.80
    tracks
    0.80
    Activations Density 0.622%

    No Known Activations