© 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. 11-RES-JB
    11. 106
    Prev
    Next
    INDEX
    Explanations

    number combinations representing technological configurations or specifications

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations of values related to technology and computing systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guinness
    -0.80
     Triumph
    -0.64
     scrimmage
    -0.63
     777
    -0.63
     Honda
    -0.61
     Marina
    -0.61
     Hoo
    -0.61
     Upton
    -0.61
    ãģĤ
    -0.60
     Ful
    -0.60
    POSITIVE LOGITS
    dimensional
    1.51
    step
    1.22
    factor
    1.22
    sided
    1.18
    player
    1.17
    byte
    1.17
    click
    1.16
    layer
    1.15
    column
    1.14
    phase
    1.14
    Activations Density 0.134%

    No Known Activations