© 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. 11-RES-JB
    11. 20885
    Prev
    Next
    INDEX
    Explanations

    phrases related to feelings or emotions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rolet
    -0.73
    Export
    -0.71
    yright
    -0.68
    iosyncr
    -0.67
    kaya
    -0.66
    igmatic
    -0.66
    iary
    -0.66
    origin
    -0.65
    angler
    -0.65
    oslov
    -0.64
    POSITIVE LOGITS
     confronted
    1.41
     faced
    1.31
     someone
    1.06
    soever
    1.05
     somebody
    1.05
     they
    0.94
     encountering
    0.93
     pressed
    0.91
     others
    0.91
     we
    0.90
    Activations Density 0.122%

    No Known Activations