© 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. 6-RES-JB
    11. 17782
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative behaviors or consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intoxication, marital relationships, and feelings of being lost or frustrated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WB
    -0.70
    chief
    -0.65
     Ng
    -0.61
     testament
    -0.61
    abiding
    -0.60
    ighth
    -0.60
    audi
    -0.59
    ibia
    -0.57
     entirety
    -0.56
     Founding
    -0.55
    POSITIVE LOGITS
    retty
    0.91
    ãĤ¼
    0.83
     sidx
    0.74
    ocobo
    0.71
    quished
    0.70
    ipolar
    0.69
    */(
    0.68
    ptin
    0.68
    ér
    0.67
    ierrez
    0.67
    Activations Density 0.100%

    No Known Activations