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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22375
    Prev
    Next
    INDEX
    Explanations

    mentions of Members of Parliament (MPs)

    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 @ 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
     endeavor
    -0.76
    eval
    -0.73
    atl
    -0.72
    eanor
    -0.68
     marvelous
    -0.66
    aler
    -0.65
    colored
    -0.64
    gru
    -0.64
    --
    -0.64
     fulfillment
    -0.63
    POSITIVE LOGITS
     MPs
    3.64
     councillors
    2.12
     MEP
    2.12
     parliament
    1.95
     Ministers
    1.90
     Parliament
    1.86
     Parliamentary
    1.77
     MP
    1.76
     senators
    1.75
     ministers
    1.73
    Activations Density 0.006%

    No Known Activations