© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10130
    Prev
    Next
    INDEX
    Explanations

    references to printing or sharing content online

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Print" in various contexts

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

    No Comments

    Negative Logits
    onite
    -0.78
    assic
    -0.72
    steen
    -0.67
    arios
    -0.63
    opoulos
    -0.62
     Oaks
    -0.62
    ocratic
    -0.62
    uster
    -0.62
    peak
    -0.61
    ascular
    -0.60
    POSITIVE LOGITS
     Print
    1.09
    Print
    1.06
    Writer
    0.89
     Seym
    0.89
    sheet
    0.86
    sburgh
    0.85
     Paste
    0.80
    Screen
    0.76
    ername
    0.76
    cies
    0.75
    Activations Density 0.017%

    No Known Activations