© 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. 7-RES-JB
    11. 18865
    Prev
    Next
    INDEX
    Explanations

    mentions of Members of Parliament (MPs) and their activities or positions

    oai_token-act-pair · gpt-3.5-turbo

    references to Members of Parliament (MPs)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stal
    -0.93
    istically
    -0.74
    idad
    -0.73
    gers
    -0.69
    renheit
    -0.67
    istic
    -0.66
    ppo
    -0.63
    xual
    -0.63
    clusively
    -0.62
    iHUD
    -0.62
    POSITIVE LOGITS
    LAB
    1.02
    rieve
    0.94
    rint
    0.88
    PLIC
    0.86
    MP
    0.82
    DOM
    0.81
    RA
    0.79
    AC
    0.79
    AA
    0.78
    UV
    0.78
    Activations Density 0.017%

    No Known Activations