© 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. 2-RES-JB
    11. 17617
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations or political institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the location "Westminster."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onies
    -0.80
    osphere
    -0.77
    href
    -0.74
    rahim
    -0.74
    vana
    -0.73
     Kinnikuman
    -0.71
    ony
    -0.70
    alach
    -0.69
    avorable
    -0.68
    uated
    -0.67
    POSITIVE LOGITS
     Abbey
    1.12
    minster
    0.98
    bridge
    0.91
     Westminster
    0.88
    mere
    0.83
    boro
    0.80
    shire
    0.75
    mouth
    0.73
    bledon
    0.73
    borough
    0.71
    Activations Density 0.005%

    No Known Activations