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. 19594
    Prev
    Next
    INDEX
    Explanations

    action verbs related to changes or movements

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to changes or transitions in policies and funding

    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
    Eva
    -0.81
     Frie
    -0.68
    Ñı
    -0.67
    fect
    -0.67
    Result
    -0.65
    Perfect
    -0.65
    Sensor
    -0.65
     Janeiro
    -0.65
    spot
    -0.62
     Correspond
    -0.62
    POSITIVE LOGITS
     moratorium
    1.01
     altogether
    0.84
     outright
    0.77
     arsen
    0.75
     abol
    0.75
     bans
    0.74
     abolished
    0.73
     downs
    0.72
    ansk
    0.72
     decriminal
    0.72
    Activations Density 0.463%

    No Known Activations