© 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. 0-RES-JB
    11. 1577
    Prev
    Next
    INDEX
    Explanations

    words related to impact or strong emotions, possibly with a focus on physical force

    oai_token-act-pair · gpt-3.5-turbo

    words related to structural elements or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Irvine
    -0.76
     Birch
    -0.70
    ulhu
    -0.69
     SAS
    -0.69
     Kung
    -0.67
     Amtrak
    -0.67
     Garfield
    -0.67
    edi
    -0.67
     casinos
    -0.66
     shuffle
    -0.65
    POSITIVE LOGITS
    stru
    3.00
     maiden
    1.97
    rera
    1.67
     Dre
    1.28
    itten
    1.25
     menstru
    1.17
    opausal
    1.10
     ov
    1.06
     Maiden
    0.96
     menstrual
    0.90
    Activations Density 0.044%

    No Known Activations