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. 4-RES-JB
    6. 9807
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to politics and society

    oai_token-act-pair · gpt-3.5-turbo

    references to systemic societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )</
    -0.86
    Pokemon
    -0.79
     Poké
    -0.73
    Poké
    -0.71
    Delivery
    -0.67
    Eat
    -0.66
    Ear
    -0.66
     [|
    -0.64
    Custom
    -0.64
    Awesome
    -0.63
    POSITIVE LOGITS
     moreover
    0.97
     neocons
    0.97
     Chomsky
    0.97
     liberals
    0.92
    omsky
    0.88
     imperialist
    0.87
     socialists
    0.86
     rhet
    0.85
     ideologically
    0.84
     rhetorical
    0.81
    Activations Density 1.840%

    No Known Activations