© 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. 4-RES-JB
    11. 17066
    Prev
    Next
    INDEX
    Explanations

    words related to political events or activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and discussions related to town hall events

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

    No Comments

    Negative Logits
     Verb
    -0.74
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
    orius
    -0.68
    href
    -0.68
    riott
    -0.66
     UNIVERS
    -0.64
    İĭ
    -0.63
     Argon
    -0.63
    Ö¼
    -0.62
     Templ
    -0.61
    POSITIVE LOGITS
    ipeg
    0.73
    bnb
    0.67
    iser
    0.64
    aza
    0.63
    iversary
    0.63
     meetings
    0.62
    istan
    0.61
    woman
    0.61
    itzer
    0.61
    aturdays
    0.60
    Activations Density 0.045%

    No Known Activations