© 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. 10-RES-JB
    11. 11640
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions or topics of interest

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the definite article "the" and its repeated use in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icip
    -0.75
    oslav
    -0.75
    teenth
    -0.70
    leased
    -0.69
    outheastern
    -0.68
    LI
    -0.64
    ordinate
    -0.64
     IMAGES
    -0.64
    edia
    -0.63
    HAM
    -0.63
    POSITIVE LOGITS
     equation
    1.40
     fray
    1.31
     matter
    1.30
     situation
    1.25
     affair
    1.19
     ordeal
    1.16
     story
    1.15
     puzzle
    1.14
     tale
    1.14
     madness
    1.14
    Activations Density 0.277%

    No Known Activations