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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12306
    Prev
    Next
    INDEX
    Explanations

    phrases related to political negotiations and discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to government or institutional actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    his
    -0.89
    Its
    -0.77
    His
    -0.76
     Himself
    -0.75
    him
    -0.74
    fuck
    -0.73
    He
    -0.71
    issance
    -0.70
    Stats
    -0.66
     Its
    -0.66
    POSITIVE LOGITS
     they
    1.03
     their
    1.01
     negotiators
    0.96
     themselves
    0.96
     Thursday
    0.92
     respectively
    0.92
     Wednesday
    0.91
    they
    0.91
     Tuesday
    0.91
     They
    0.89
    Activations Density 0.908%

    No Known Activations