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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 3993
    Prev
    Next
    INDEX
    Explanations

    phrases related to tightening rules or grip on something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to regulation and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agne
    -0.78
     Islands
    -0.75
     Frie
    -0.69
     Forgotten
    -0.69
     Newspaper
    -0.68
    eri
    -0.68
    aign
    -0.65
    rum
    -0.65
     Amelia
    -0.64
     Cork
    -0.64
    POSITIVE LOGITS
     tightening
    1.16
     tightened
    1.07
     tighten
    1.05
     throttle
    0.98
     tension
    0.96
     screws
    0.95
     grip
    0.95
     tighter
    0.91
     restrictions
    0.88
     toler
    0.87
    Activations Density 0.033%

    No Known Activations