Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20925
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "American" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "American."

    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
    heed
    -0.82
    razil
    -0.72
    pots
    -0.70
    */(
    -0.70
    NB
    -0.70
    Prev
    -0.67
    aday
    -0.67
    sets
    -0.67
    fill
    -0.65
    idious
    -0.65
    POSITIVE LOGITS
     Airlines
    1.16
     Idol
    1.11
     Samoa
    1.08
     Legion
    0.95
     Express
    0.93
     Revolution
    0.92
     Federation
    0.92
    ICAN
    0.92
     Dream
    0.91
     Indian
    0.86
    Activations Density 0.070%

    No Known Activations