© 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. 5027
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions that happen suddenly and energetically

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a dramatic entrance or emergence

    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
    ļéĨĴ
    -0.67
     Factors
    -0.65
    manship
    -0.64
    ryu
    -0.62
    trip
    -0.60
    £
    -0.59
    thood
    -0.58
    trust
    -0.58
    ials
    -0.57
    essors
    -0.56
    POSITIVE LOGITS
    wards
    0.72
     flames
    0.71
    Downloadha
    0.68
     hither
    0.68
     ecstasy
    0.67
    ibrary
    0.67
     shores
    0.67
     Archdemon
    0.65
     applause
    0.65
    nova
    0.65
    Activations Density 0.282%

    No Known Activations