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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 6937
    Prev
    Next
    INDEX
    Explanations

    values or measurements often seen in scientific research

    oai_token-act-pair · gpt-3.5-turbo

    scientific and statistical data related to medical research

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

    No Comments

    Negative Logits
    NetMessage
    -0.94
     Sovere
    -0.86
    Story
    -0.78
    soDeliveryDate
    -0.78
    ooks
    -0.76
    ulhu
    -0.76
    Rust
    -0.71
     owes
    -0.69
    pmwiki
    -0.69
     somew
    -0.67
    POSITIVE LOGITS
     âĪ¼
    1.15
     âĪĴ
    1.12
     (âĪĴ
    1.11
    âĪĴ
    1.02
     assay
    0.98
     β
    0.97
     âī¥
    0.93
     ±
    0.92
     âī¤
    0.90
     remission
    0.87
    Activations Density 0.533%

    No Known Activations