© 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. 9-RES-JB
    11. 7497
    Prev
    Next
    INDEX
    Explanations

    words related to organization or structure

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "order" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peria
    -0.75
    ãĤ©
    -0.73
    SG
    -0.72
    ãĥ©
    -0.72
    tu
    -0.72
    rities
    -0.70
    vae
    -0.70
    ipedia
    -0.70
    irst
    -0.69
    sonian
    -0.66
    POSITIVE LOGITS
    lies
    1.39
    liness
    1.17
    etary
    0.79
    books
    0.75
    book
    0.74
    ylum
    0.74
    eering
    0.74
    hend
    0.72
    eous
    0.71
     discipl
    0.70
    Activations Density 0.040%

    No Known Activations