© 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. 2-RES-JB
    11. 15275
    Prev
    Next
    INDEX
    Explanations

    words related to laws or governmental acts

    oai_token-act-pair · gpt-3.5-turbo

    words related to authority or governmental oversight

    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
    STON
    -0.80
    âĵĺ
    -0.71
    syn
    -0.69
    efined
    -0.68
    edo
    -0.67
    rador
    -0.64
    yright
    -0.64
    eatures
    -0.64
    ETA
    -0.63
    sid
    -0.62
    POSITIVE LOGITS
    ence
    1.12
    ment
    0.90
    llor
    0.87
    mble
    0.86
    phal
    0.85
    ENCE
    0.84
    ance
    0.81
    rance
    0.80
    ences
    0.78
    rences
    0.78
    Activations Density 0.017%

    No Known Activations