© 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. 9-RES-JB
    11. 18346
    Prev
    Next
    INDEX
    Explanations

    activation phrases related to requesting a user's attention

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or collective perspective, particularly the use of "me" and "us"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iaries
    -0.61
     suicides
    -0.60
    bidden
    -0.59
    _.
    -0.56
    ibrary
    -0.55
    aks
    -0.54
    ranch
    -0.54
    icion
    -0.53
     fragmentation
    -0.52
    hedon
    -0.52
    POSITIVE LOGITS
    rina
    0.65
    adow
    0.64
    Widget
    0.63
     Thumbnails
    0.60
    img
    0.59
    azz
    0.56
    ocol
    0.55
    tle
    0.55
    borough
    0.55
    dam
    0.54
    Activations Density 0.019%

    No Known Activations