© 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. 9-RES-JB
    11. 20847
    Prev
    Next
    INDEX
    Explanations

    the word "never" followed by a verb indicating a negative action or statement

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases starting with "Never."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nikov
    -0.69
    redients
    -0.68
    ahime
    -0.64
    ?????-
    -0.63
    eers
    -0.59
    emia
    -0.58
    iency
    -0.58
    otle
    -0.57
    atics
    -0.57
     AAA
    -0.57
    POSITIVE LOGITS
    theless
    1.77
    mind
    1.14
    winter
    1.04
     ceases
    0.91
     mind
    0.87
     hesitate
    0.84
     underestimate
    0.80
     EVER
    0.78
    again
    0.75
     forgotten
    0.74
    Activations Density 0.042%

    No Known Activations