© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7034
    Prev
    Next
    INDEX
    Explanations

    references to political parties

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political parties

    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
     Tile
    -0.73
     Wheat
    -0.73
     Drake
    -0.70
    angelo
    -0.69
     DOI
    -0.69
    alam
    -0.68
     Deter
    -0.68
    htaking
    -0.66
     Monroe
    -0.65
     Ridge
    -0.64
    POSITIVE LOGITS
     affiliation
    0.93
    leader
    0.91
    Leader
    0.87
    goers
    0.83
     insiders
    0.82
     leader
    0.82
     affili
    0.80
    agogue
    0.80
     advoc
    0.79
     leaders
    0.79
    Activations Density 0.032%

    No Known Activations