© 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. 9-RES-JB
    11. 15440
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events and figures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "first" along with references to notable historical or cultural entities

    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
     abound
    -0.70
    Gameplay
    -0.68
    enance
    -0.67
    ãĥĥ
    -0.65
    affer
    -0.64
    ensitivity
    -0.63
    ruciating
    -0.62
    contin
    -0.62
    nature
    -0.62
     Powers
    -0.61
    POSITIVE LOGITS
     EVER
    1.01
     imaginable
    1.00
     ever
    0.96
     sighting
    0.90
     installment
    0.83
    ever
    0.76
     iteration
    0.76
     incarnation
    0.76
     Ever
    0.73
     foray
    0.73
    Activations Density 0.285%

    No Known Activations