© 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. 11-RES-JB
    11. 21784
    Prev
    Next
    INDEX
    Explanations

    calls to action inviting someone to be part of a group or activity

    oai_token-act-pair · gpt-3.5-turbo

    calls to action for joining or subscribing to various groups and newsletters

    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
     discharge
    -0.69
    undai
    -0.61
     termination
    -0.61
    mination
    -0.60
     forgiven
    -0.58
    icz
    -0.57
     subord
    -0.57
    wrapper
    -0.57
     grounding
    -0.56
     griev
    -0.56
    POSITIVE LOGITS
     us
    0.88
     Corey
    0.71
     Leading
    0.70
    OWN
    0.70
     Us
    0.69
     Forces
    0.69
     millions
    0.68
     Date
    0.68
     thousands
    0.67
     me
    0.66
    Activations Density 0.027%

    No Known Activations