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. 11026
    Prev
    Next
    INDEX
    Explanations

    references to political figures and activities, particularly focusing on allegations or actions involving them

    oai_token-act-pair · gpt-3.5-turbo

    content related to investigations and evidence in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Franç
    -0.71
    vier
    -0.70
    theless
    -0.69
     "$:/
    -0.67
    mania
    -0.63
    ruary
    -0.63
    etheless
    -0.62
     nonetheless
    -0.60
    !--
    -0.60
    tions
    -0.58
    POSITIVE LOGITS
     Kavanaugh
    0.81
     Rosenstein
    0.69
    FBI
    0.65
     Mueller
    0.57
    Iv
    0.57
    Ford
    0.56
    ĵ
    0.54
    Top
    0.54
    ombs
    0.54
    opened
    0.53
    Activations Density 0.029%

    No Known Activations