© 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. 3-RES-JB
    11. 5223
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative outcomes or failure

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hopelessness or failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.72
    overed
    -0.68
    ATT
    -0.67
    EMA
    -0.63
    akers
    -0.63
    MA
    -0.62
    OH
    -0.62
    anon
    -0.61
    Allen
    -0.61
    aque
    -0.61
    POSITIVE LOGITS
     doomed
    1.10
     releg
    0.76
    iflower
    0.72
     undermin
    0.71
     downfall
    0.70
     doom
    0.70
     desper
    0.70
    itude
    0.69
    icter
    0.68
     miser
    0.68
    Activations Density 0.013%

    No Known Activations