© 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. 6-RES-JB
    11. 3617
    Prev
    Next
    INDEX
    Explanations

    names of medical conditions and related terms like "projected to get" and "are still in demand."

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.69
     Vaugh
    -0.65
     Kardash
    -0.64
     vulner
    -0.59
     thous
    -0.57
    accompan
    -0.57
     mathemat
    -0.55
    —-
    -0.55
     marqu
    -0.54
     advoc
    -0.53
    POSITIVE LOGITS
    rael
    0.67
    Ĥª
    0.64
    wolf
    0.60
    Ĥİ
    0.60
    osures
    0.60
    ovie
    0.59
    icidal
    0.58
    ometric
    0.58
    metics
    0.58
    hee
    0.57
    Activations Density 0.354%

    No Known Activations