© 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. 9-RES-JB
    11. 18220
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological processes and methods

    oai_token-act-pair · gpt-3.5-turbo

    mentions of characteristics related to technology or media

    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
     Beaver
    -0.71
     Doors
    -0.69
     Inher
    -0.67
    neath
    -0.66
     Sons
    -0.66
     Confederation
    -0.66
     Jub
    -0.66
    quished
    -0.65
    english
    -0.64
     Visitors
    -0.64
    POSITIVE LOGITS
     eliminates
    1.24
     reduces
    1.22
     avoids
    1.17
     removes
    1.15
     produces
    1.11
     tends
    1.11
     performs
    1.10
     requires
    1.08
     entails
    1.08
     allows
    1.08
    Activations Density 0.514%

    No Known Activations