© 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. 11-RES-JB
    11. 1251
    Prev
    Next
    INDEX
    Explanations

    words related to news articles and subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to LGBT news and stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maybe
    -0.58
     undecided
    -0.55
     spont
    -0.55
     unlikely
    -0.54
    rather
    -0.53
     maybe
    -0.53
     seldom
    -0.51
     Nope
    -0.51
    Or
    -0.50
    unknown
    -0.50
    POSITIVE LOGITS
    illance
    0.60
    eu
    0.58
    cester
    0.55
    boss
    0.54
    ascus
    0.53
    venants
    0.52
    dot
    0.51
     è£ıç
    0.50
    killer
    0.50
     stronghold
    0.49
    Activations Density 0.558%

    No Known Activations