© 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. 6-RES-JB
    11. 10706
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotional reactions or intense actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "crazy" and related terms

    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
    manship
    -0.83
    REDACTED
    -0.74
    nikov
    -0.71
    layer
    -0.71
    acity
    -0.71
     Covenant
    -0.71
     Instruments
    -0.69
     Annotations
    -0.68
     ANGEL
    -0.66
     Dragonbound
    -0.64
    POSITIVE LOGITS
    igslist
    1.46
    pload
    1.08
    pton
    1.00
    fters
    1.00
    ving
    0.93
    fter
    0.86
    issy
    0.84
    ãĥ£
    0.84
    vette
    0.81
    arding
    0.80
    Activations Density 0.034%

    No Known Activations