© 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. 9416
    Prev
    Next
    INDEX
    Explanations

    words related to experiencing difficulty or hardship

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "struggled" and its variations, indicating difficulties or challenges

    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
    chnology
    -0.76
    \\\\\\\\\\\\\\\\
    -0.72
    ovo
    -0.72
    gone
    -0.72
    resy
    -0.69
    ahu
    -0.66
    lav
    -0.65
    jiang
    -0.65
    nesty
    -0.64
    othy
    -0.63
    POSITIVE LOGITS
     miser
    0.97
     horribly
    0.76
     dogged
    0.75
    hirt
    0.73
    nesses
    0.72
     badly
    0.71
     struggling
    0.70
    ingly
    0.69
     financially
    0.69
    antically
    0.69
    Activations Density 0.028%

    No Known Activations