© 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. 9-RES-JB
    11. 20776
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing services or resources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "provide" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lasses
    -0.65
    Reloaded
    -0.63
    dress
    -0.62
     moss
    -0.61
     stuffing
    -0.59
    RANT
    -0.58
     dough
    -0.58
    mare
    -0.58
     Goo
    -0.58
     Palm
    -0.57
    POSITIVE LOGITS
    idence
    1.52
    iders
    1.49
    isions
    1.36
    iding
    1.36
    incial
    1.35
    idences
    1.28
    ince
    1.27
    idential
    1.23
    ided
    1.21
    ide
    1.20
    Activations Density 0.035%

    No Known Activations