© 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. 20016
    Prev
    Next
    INDEX
    Explanations

    phrases related to decisions or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "move" in various contexts

    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
    Condition
    -0.67
    omial
    -0.63
     Koran
    -0.62
    aez
    -0.62
    vana
    -0.62
    oola
    -0.61
    vae
    -0.60
     sqor
    -0.60
     attm
    -0.59
    icum
    -0.57
    POSITIVE LOGITS
     towards
    1.05
     toward
    1.04
    able
    0.91
    backs
    0.87
    over
    0.79
    ments
    0.79
     forward
    0.77
    rers
    0.75
    iton
    0.75
    overs
    0.74
    Activations Density 0.037%

    No Known Activations