© 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. 19594
    Prev
    Next
    INDEX
    Explanations

    phrases associated with actions or decisions being authorized or determined by someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "by" used in various contexts

    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
    asy
    -0.76
    ational
    -0.67
    SPONSORED
    -0.65
    bia
    -0.63
    >[
    -0.62
    ndum
    -0.61
    iple
    -0.61
    atem
    -0.60
    itled
    -0.59
    igrate
    -0.59
    POSITIVE LOGITS
     virtue
    1.30
    laws
    0.99
    products
    0.96
     fiat
    0.85
    gone
    0.82
    product
    0.76
     multiplying
    0.76
     leaps
    0.73
     afar
    0.71
     adding
    0.70
    Activations Density 0.246%

    No Known Activations