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

    Neuronpedia

    Jacobian LensNEW
    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. 3888
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to proper nouns, possibly names or titles

    oai_token-act-pair · gpt-3.5-turbo

    the term "ors" in various contexts, indicating a focus on elements related to options or alternatives

    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
    lyak
    -0.74
    mons
    -0.70
    esville
    -0.68
    assadors
    -0.66
    sters
    -0.66
    ctors
    -0.66
    lished
    -0.66
    OTAL
    -0.66
    let
    -0.65
    Fra
    -0.63
    POSITIVE LOGITS
    hips
    1.36
    hift
    1.14
    pring
    0.89
    mith
    0.83
    hip
    0.83
    ially
    0.82
    omething
    0.81
    chid
    0.81
    EMENT
    0.81
    pheus
    0.78
    Activations Density 0.054%

    No Known Activations