© 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. 3-RES-JB
    11. 3326
    Prev
    Next
    INDEX
    Explanations

    words related to making changes or adjustments in various contexts, such as business or technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to changing direction or strategy, particularly in business contexts

    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
    TPS
    -0.66
    WAY
    -0.66
     captcha
    -0.64
    soever
    -0.63
    à¦
    -0.63
    Merit
    -0.63
    Interstitial
    -0.62
    HOU
    -0.62
    CLA
    -0.62
    weeney
    -0.58
    POSITIVE LOGITS
     pivot
    1.16
    ivot
    1.07
     piv
    1.06
    oting
    0.88
    ilus
    0.86
    olate
    0.86
    oted
    0.84
    olicy
    0.83
    itures
    0.77
    olitics
    0.72
    Activations Density 0.010%

    No Known Activations