© 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. 1-RES-JB
    11. 22791
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, particularly involving the nose

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "nos" and related variations in the context of specific subjects or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥį
    -0.87
    estine
    -0.80
    Reward
    -0.78
    IBLE
    -0.74
    RAL
    -0.71
     Abedin
    -0.69
    ersed
    -0.68
    ãĥ¼ãĤ¯
    -0.68
    SG
    -0.67
    Aren
    -0.67
    POSITIVE LOGITS
    opy
    0.84
    ignt
    0.83
    onna
    0.80
    emon
    0.78
     millenn
    0.77
    oln
    0.77
    atts
    0.77
    opes
    0.76
    urches
    0.75
    chy
    0.75
    Activations Density 0.030%

    No Known Activations