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. 0-RES-JB
    6. 9064
    Prev
    Next
    INDEX
    Explanations

    proper nouns of political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Champ
    -0.82
     Champ
    -0.76
    ihad
    -0.70
    vic
    -0.68
    GV
    -0.68
     Moor
    -0.68
    Group
    -0.66
    Bridge
    -0.66
    Active
    -0.65
    VC
    -0.65
    POSITIVE LOGITS
     Abe
    2.79
     Hodg
    2.11
    abol
    1.26
     Hannity
    1.12
    eln
    1.08
     Spicer
    1.04
     gag
    0.96
     Reprodu
    0.91
     Hick
    0.90
     POLITICO
    0.89
    Activations Density 0.037%

    No Known Activations