© 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. 2-RES-JB
    11. 23815
    Prev
    Next
    INDEX
    Explanations

    the word "Smith" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to an individual named Smith

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ça
    -0.68
    ocard
    -0.66
    razil
    -0.66
     narciss
    -0.63
     Greenpeace
    -0.63
     UNESCO
    -0.62
     dear
    -0.62
    terness
    -0.61
     kindred
    -0.61
     ABV
    -0.61
    POSITIVE LOGITS
    sonian
    1.50
    son
    0.96
    gren
    0.92
    Smith
    0.90
    anity
    0.86
    sburg
    0.84
    smanship
    0.83
     Smith
    0.81
    andowski
    0.80
    iak
    0.79
    Activations Density 0.010%

    No Known Activations