© 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. 15658
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and technology upgrades

    oai_token-act-pair · gpt-3.5-turbo

    references to specific systems, packages, and organizational structures

    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
    âĹ¼
    -0.76
    appropriate
    -0.68
    externalActionCode
    -0.67
    TPPStreamerBot
    -0.65
    é¾įå¥ij士
    -0.64
    +.
    -0.59
    oyal
    -0.59
    ãģĦ
    -0.59
    xious
    -0.57
    ãĤ¤ãĥĪ
    -0.57
    POSITIVE LOGITS
     consists
    1.32
     comprises
    1.25
     contains
    1.20
     consisted
    1.17
     has
    1.13
     is
    1.07
     encompasses
    1.06
     continues
    1.06
     revolves
    1.06
     disappears
    1.05
    Activations Density 0.483%

    No Known Activations