© 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. 19805
    Prev
    Next
    INDEX
    Explanations

    words with the sequence "oc" followed by the number "9" or "10"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "oc" 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
    ĪĴ
    -0.78
     Verse
    -0.78
     Chimera
    -0.68
     Furious
    -0.68
     Gemini
    -0.66
     Gork
    -0.65
     Shepard
    -0.64
     Hulk
    -0.64
     Maker
    -0.63
     Romantic
    -0.63
    POSITIVE LOGITS
    entric
    1.29
    abulary
    1.21
    onut
    1.13
    orpor
    1.10
    lean
    1.10
    hester
    1.07
    rim
    1.06
    airo
    1.06
    urrencies
    1.04
    ombat
    1.04
    Activations Density 0.011%

    No Known Activations