© 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. 0-RES-JB
    11. 16601
    Prev
    Next
    INDEX
    Explanations

    words related to a specific medical condition starting with "trimethy."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Al-Madinah" and related variations in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CFR
    -0.70
    Press
    -0.62
     cro
    -0.59
     reflex
    -0.59
     VIDEO
    -0.59
     Mé
    -0.58
    Japanese
    -0.58
    Journal
    -0.58
     cerv
    -0.57
     Trophy
    -0.57
    POSITIVE LOGITS
    adin
    4.43
    addin
    2.12
    pox
    1.12
    vor
    1.05
    adesh
    0.95
    uria
    0.93
    asel
    0.92
    andre
    0.91
    ilst
    0.90
    aden
    0.89
    Activations Density 0.034%

    No Known Activations