© 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. 18270
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantities and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    numerical ranges and values related to measurements or statistics

    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
    ronic
    -0.67
    awan
    -0.62
    unta
    -0.59
    NetMessage
    -0.57
    agne
    -0.56
    sers
    -0.56
    fecture
    -0.56
    phalt
    -0.56
    hett
    -0.56
    olkien
    -0.55
    POSITIVE LOGITS
     0
    1.32
     50
    1.24
     500
    1.24
     1000
    1.23
     5000
    1.23
     250
    1.22
     10
    1.21
     60
    1.20
     10000
    1.20
     1024
    1.20
    Activations Density 0.531%

    No Known Activations