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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23189
    Prev
    Next
    INDEX
    Explanations

    medical conditions or treatments related to diagnostics

    oai_token-act-pair · gpt-3.5-turbo

    medical and anatomical terms, as well as specific objects or concepts related to health

    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
    idth
    -0.51
    âĢ¢âĢ¢
    -0.50
    ãĥķãĤ©
    -0.50
    ++++
    -0.50
    ————————
    -0.48
     Acqu
    -0.46
    ãĤ¢ãĥ«
    -0.45
    mx
    -0.45
    nos
    -0.45
    arsity
    -0.45
    POSITIVE LOGITS
     rul
    0.60
    bard
    0.59
    ongyang
    0.54
    bryce
    0.53
    utenberg
    0.53
    bol
    0.50
     cryst
    0.49
     minion
    0.48
     exting
    0.48
    enhagen
    0.48
    Activations Density 1.798%

    No Known Activations