© 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. 1455
    Prev
    Next
    INDEX
    Explanations

    phrases related to doctors

    oai_token-act-pair · gpt-3.5-turbo

    references to medical professionals

    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
     actionGroup
    -0.78
     Leilan
    -0.78
    LOAD
    -0.72
     âĺħ
    -0.70
    SHIP
    -0.67
     rout
    -0.66
    OPA
    -0.63
    HUD
    -0.63
     Territories
    -0.63
     Ranked
    -0.62
    POSITIVE LOGITS
    inker
    1.04
    umin
    1.04
    inks
    1.00
    icist
    0.96
    acist
    0.94
    unks
    0.93
    inking
    0.93
    agic
    0.92
    ifts
    0.92
    anium
    0.91
    Activations Density 0.014%

    No Known Activations