© 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. 4545
    Prev
    Next
    INDEX
    Explanations

    references to specific political or governmental entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political parties or assemblies

    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
     Kear
    -0.68
     traffickers
    -0.66
     Jenner
    -0.65
     Viking
    -0.65
    ologically
    -0.64
     srf
    -0.63
     Mayhem
    -0.63
    omic
    -0.63
     Pearl
    -0.62
    gotten
    -0.61
    POSITIVE LOGITS
     Sabha
    1.28
     Speaker
    0.93
    rats
    0.92
    ature
    0.86
    ataka
    0.80
    OTUS
    0.78
    ecast
    0.78
    istani
    0.78
    track
    0.77
    holders
    0.77
    Activations Density 0.004%

    No Known Activations