© 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. 7442
    Prev
    Next
    INDEX
    Explanations

    mentions of names, particularly those starting with "Tre"

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to measurements or evaluations

    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
    ategory
    -0.75
    nect
    -0.72
     skim
    -0.66
     Tsukuyomi
    -0.64
    HAHA
    -0.64
     disadvant
    -0.63
    ortium
    -0.62
     challeng
    -0.60
    eming
    -0.58
    AIDS
    -0.58
    POSITIVE LOGITS
    inarily
    0.74
    initialized
    0.69
    andum
    0.69
    andise
    0.68
    zx
    0.67
    edit
    0.65
    ese
    0.63
    ousy
    0.63
    uries
    0.62
    horn
    0.62
    Activations Density 0.196%

    No Known Activations