© 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. 3-RES-JB
    11. 15343
    Prev
    Next
    INDEX
    Explanations

    specific references to a technological or industry-related term

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "EM" or related concepts within a specific context

    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
    netflix
    -0.86
     Kubrick
    -0.80
     Penguin
    -0.71
     Kissinger
    -0.70
     Rockies
    -0.67
     skirts
    -0.66
     Strauss
    -0.65
    lihood
    -0.63
    Thumbnail
    -0.63
    rowing
    -0.62
    POSITIVE LOGITS
    ERG
    1.28
    BLE
    1.04
    ISSION
    0.98
    ILY
    0.97
    achine
    0.96
    IX
    0.95
    igrants
    0.95
    EMBER
    0.94
    icro
    0.92
    ERAL
    0.92
    Activations Density 0.008%

    No Known Activations