© 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. 8-RES-JB
    11. 7721
    Prev
    Next
    INDEX
    Explanations

    instances of the word "program" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to programs and programming-related terminology

    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
    pick
    -0.74
     dilig
    -0.73
     humidity
    -0.64
    uple
    -0.64
    picking
    -0.64
    âĶĢâĶĢâĶĢâĶĢ
    -0.63
    ModLoader
    -0.63
     statues
    -0.63
    Boss
    -0.60
     volcan
    -0.60
    POSITIVE LOGITS
    mable
    2.09
    matic
    1.63
    matically
    1.63
    mers
    1.14
     Gutenberg
    1.09
    atically
    1.05
    mes
    1.04
    ming
    0.94
    atical
    0.91
    atics
    0.88
    Activations Density 0.044%

    No Known Activations