© 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 EvalsExportsinterp-engineNEWAPI 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. 9398
    Prev
    Next
    INDEX
    Explanations

    references to physically hanging or being hung

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hang" and its variations in various contexts

    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
    姫
    -0.87
    ãĤ¡
    -0.85
    ibel
    -0.84
    ledged
    -0.79
    theless
    -0.75
     GENERAL
    -0.74
    ãĥĨãĤ£
    -0.74
    ãĥ¼ãĥ³
    -0.72
    eele
    -0.70
     Abrams
    -0.67
    POSITIVE LOGITS
    rily
    0.96
     hang
    0.83
     hanging
    0.83
    hang
    0.83
     onto
    0.82
     upside
    0.81
    river
    0.81
    mast
    0.80
     Hang
    0.79
     baskets
    0.78
    Activations Density 0.032%

    No Known Activations