© 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. 8-RES-JB
    11. 7867
    Prev
    Next
    INDEX
    Explanations

    proper nouns like names of newspapers and cities

    oai_token-act-pair · gpt-3.5-turbo

    closing parentheses and other similar punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    checked
    -0.69
     correl
    -0.67
     fronts
    -0.66
    gae
    -0.65
    hang
    -0.65
    amba
    -0.62
    worms
    -0.62
    poon
    -0.60
    bomb
    -0.60
    bred
    -0.59
    POSITIVE LOGITS
     Story
    0.76
     More
    0.70
     ï
    0.68
     Related
    0.66
     FILE
    0.66
     Cohn
    0.65
     Mesa
    0.63
     Loading
    0.63
     Hundreds
    0.63
     Highlights
    0.62
    Activations Density 0.063%

    No Known Activations