© 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. 8-RES-JB
    11. 18688
    Prev
    Next
    INDEX
    Explanations

    phrases where something is being named or referred to as a specific label or term

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "call it" in various contexts

    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
    ashington
    -0.74
    hung
    -0.69
     offend
    -0.68
    taboola
    -0.67
    edia
    -0.65
    ourney
    -0.65
    abal
    -0.63
    iston
    -0.62
    itely
    -0.62
     Illustrated
    -0.62
    POSITIVE LOGITS
     bluff
    0.86
    arin
    0.68
     "#
    0.68
    EStreamFrame
    0.67
    izon
    0.64
     ``
    0.63
    selves
    0.63
     heresy
    0.62
     qu
    0.62
     parity
    0.61
    Activations Density 0.073%

    No Known Activations