© 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. 3-RES-JB
    11. 14801
    Prev
    Next
    INDEX
    Explanations

    words related to political power and leadership positions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ict" or its variations, often in contexts related to technology, communications, and information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meric
    -0.76
    lde
    -0.72
     Shelby
    -0.67
    knit
    -0.66
    grass
    -0.65
    Mid
    -0.64
     slideshow
    -0.63
    ndra
    -0.62
     Shank
    -0.62
    bury
    -0.62
    POSITIVE LOGITS
    ict
    0.94
    enance
    0.92
    о
    0.89
    ARGET
    0.88
    ainers
    0.88
    ificate
    0.87
    uple
    0.86
    rypt
    0.84
    orians
    0.82
    icts
    0.82
    Activations Density 0.011%

    No Known Activations