© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 17629
    Prev
    Next
    INDEX
    Explanations

    phrases related to punishment or condemnation

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with punitive actions or legal consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overlap
    -0.74
    ggles
    -0.71
     tilt
    -0.67
     glimps
    -0.67
     resid
    -0.66
     branching
    -0.66
     preview
    -0.64
    ynchron
    -0.64
     narrowing
    -0.63
     Rhythm
    -0.63
    POSITIVE LOGITS
     ASAP
    1.36
     lest
    0.98
     whoever
    0.89
     wherever
    0.87
     sooner
    0.84
     preferably
    0.83
     someday
    0.81
     unless
    0.81
     punishable
    0.81
     perpetrators
    0.80
    Activations Density 0.570%

    No Known Activations