© 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. 11-RES-JB
    11. 3490
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "can't help" followed by verbs or pronouns indicating involuntary actions or emotions, such as "feeling", "smile", "notice", and "staring"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "help" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sov
    -0.73
    Safe
    -0.70
    lore
    -0.70
    Home
    -0.67
    oven
    -0.66
    âĢ¢âĢ¢
    -0.64
    LAN
    -0.64
    LOS
    -0.62
    ledged
    -0.61
    yz
    -0.60
    POSITIVE LOGITS
     noticing
    1.07
     wondering
    0.90
     feeling
    0.89
     grinning
    0.86
     but
    0.85
     smiling
    0.82
     laughing
    0.81
     imagining
    0.80
     slipping
    0.78
    but
    0.76
    Activations Density 0.026%

    No Known Activations