© 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. 12-RES-JB
    11. 2953
    Prev
    Next
    INDEX
    Explanations

    words related to difficult or challenging situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    expressions of difficulty or frustration in personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ollow
    -0.61
    ph
    -0.59
    nos
    -0.59
    allery
    -0.56
    neutral
    -0.53
    na
    -0.53
    planes
    -0.52
    hover
    -0.52
    æ©Ł
    -0.52
     horm
    -0.51
    POSITIVE LOGITS
     REALLY
    0.77
     really
    0.77
     truly
    0.76
     sounded
    0.75
     become
    0.72
     becomes
    0.72
     sounding
    0.67
     actually
    0.67
     gets
    0.66
     sounds
    0.65
    Activations Density 0.158%

    No Known Activations