© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20303
    Prev
    Next
    INDEX
    Explanations

    words related to information security, political intrigue, and international relations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of clarity and importance regarding social or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.55
    ãĤ´ãĥ³
    -0.52
    FAULT
    -0.51
    ielding
    -0.50
    bia
    -0.50
    iga
    -0.49
    interstitial
    -0.48
     ("
    -0.48
    Reilly
    -0.48
    inducing
    -0.47
    POSITIVE LOGITS
     ..."
    1.16
    [/
    1.09
    ?'
    1.03
    )",
    1.02
    %"
    1.02
     â̦"
    1.01
    )"
    0.98
    ,''
    0.96
     [/
    0.93
    ),"
    0.93
    Activations Density 1.525%

    No Known Activations