© 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. 10020
    Prev
    Next
    INDEX
    Explanations

    mentions of notable names and locations in news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or specific names

    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
    ahime
    -0.70
    atown
    -0.70
    watch
    -0.68
    mand
    -0.68
    Reviewer
    -0.67
    trak
    -0.67
    onite
    -0.65
    ovie
    -0.64
    uthor
    -0.64
    mble
    -0.63
    POSITIVE LOGITS
     Cox
    0.80
     Vaugh
    0.71
     Plaza
    0.69
     Bridgewater
    0.69
     Islands
    0.69
     Meadows
    0.68
     Island
    0.67
     Chapman
    0.66
     Flame
    0.65
     Mansion
    0.64
    Activations Density 0.186%

    No Known Activations