© 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. 6836
    Prev
    Next
    INDEX
    Explanations

    loops or loop-related operations within a text

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to programming loops and iterations

    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
    alty
    -0.79
    hiro
    -0.69
    insula
    -0.65
     à¨
    -0.64
     Penguins
    -0.64
    undai
    -0.63
    assadors
    -0.63
    rov
    -0.63
     Spartans
    -0.62
    rations
    -0.61
    POSITIVE LOGITS
    back
    0.87
    ingly
    0.85
    overs
    0.81
     loop
    0.79
    ing
    0.79
    ioned
    0.78
    loop
    0.76
    door
    0.76
    Closure
    0.75
    efully
    0.74
    Activations Density 0.048%

    No Known Activations