© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13718
    Prev
    Next
    INDEX
    Explanations

    names followed by ages or specific years

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "turn" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -1.12
    assment
    -0.68
    bour
    -0.65
    DCS
    -0.60
    bons
    -0.60
     Broadcast
    -0.59
     reson
    -0.59
    Story
    -0.59
     retaining
    -0.57
    ording
    -0.57
    POSITIVE LOGITS
    coat
    0.92
     traitor
    0.89
     informant
    0.84
     inward
    0.79
     heads
    0.73
     beet
    0.72
     deaf
    0.71
     heel
    0.70
     upside
    0.68
     sideways
    0.68
    Activations Density 0.039%

    No Known Activations