© 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. 2-RES-JB
    11. 7307
    Prev
    Next
    INDEX
    Explanations

    instances where action is being called for or taken in a societal or governmental context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the need for governmental or organizational intervention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inately
    -0.69
     arsen
    -0.68
    olls
    -0.65
    olen
    -0.64
    conservancy
    -0.64
     Missile
    -0.64
     abundant
    -0.63
    YL
    -0.63
    iciency
    -0.63
     porous
    -0.63
    POSITIVE LOGITS
     action
    1.09
    uality
    0.90
    naires
    0.85
    ality
    0.84
    spection
    0.83
    bender
    0.83
    ional
    0.82
    bucks
    0.82
    ivism
    0.80
    ulatory
    0.80
    Activations Density 0.024%

    No Known Activations