© 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. 11-RES-JB
    11. 14824
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to a person named Ekman-Larsson

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and organizations in the context of events or achievements

    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
     AW
    -0.84
     Pax
    -0.84
     Aber
    -0.76
     meas
    -0.76
     ACS
    -0.74
     ABE
    -0.73
     Aj
    -0.72
     pav
    -0.71
     ASA
    -0.71
     Akira
    -0.71
    POSITIVE LOGITS
    l
    1.46
    ls
    1.41
    li
    1.38
    lt
    1.35
    lite
    1.33
    L
    1.32
    LI
    1.32
    lis
    1.32
    LS
    1.30
    lan
    1.29
    Activations Density 0.584%

    No Known Activations