© 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. 6273
    Prev
    Next
    INDEX
    Explanations

    phrases indicating success or functionality

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "works" 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
     Ce
    -0.66
    arta
    -0.64
    angular
    -0.63
    ANA
    -0.63
     Span
    -0.63
     Prim
    -0.62
    lua
    -0.62
    gran
    -0.61
    ————
    -0.61
    cele
    -0.61
    POSITIVE LOGITS
    hops
    1.42
    paces
    1.36
    heet
    1.25
    hirt
    1.19
    bench
    1.01
    omething
    0.99
    hift
    0.99
    pace
    0.97
    manship
    0.90
    uggest
    0.90
    Activations Density 0.022%

    No Known Activations