© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 23061
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific location, particularly "Westminster"

    oai_token-act-pair · gpt-3.5-turbo

    references to Westminster and its influence or relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osphere
    -0.85
    vana
    -0.79
    avorable
    -0.75
    onies
    -0.75
    alach
    -0.74
    oton
    -0.72
    rahim
    -0.71
     Kinnikuman
    -0.71
    href
    -0.71
    berman
    -0.70
    POSITIVE LOGITS
     Abbey
    1.11
    minster
    1.09
    bridge
    0.94
     Westminster
    0.92
    boro
    0.88
     Parliament
    0.81
    borough
    0.80
    mere
    0.78
     Borough
    0.76
     Yard
    0.76
    Activations Density 0.004%

    No Known Activations