© 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. 15971
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce topics or discussions

    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
    vier
    -0.74
    oris
    -0.70
    existent
    -0.68
    cloth
    -0.66
    mens
    -0.65
    İĭ
    -0.64
    INC
    -0.63
    sav
    -0.61
    nor
    -0.61
    represented
    -0.61
    POSITIVE LOGITS
     tasked
    0.69
     raining
    0.67
     comparing
    0.66
     assessing
    0.64
     flooding
    0.62
     undone
    0.61
     crunch
    0.61
     regards
    0.61
     pouring
    0.60
     knocking
    0.60
    Activations Density 0.030%

    No Known Activations