© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12006
    Prev
    Next
    INDEX
    Explanations

    Italian or Italian-sounding names and terms

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to "lu" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iffs
    -0.80
    nard
    -0.74
    ublic
    -0.70
    framework
    -0.66
    ificial
    -0.66
    grounds
    -0.66
     Dispatch
    -0.64
    lessness
    -0.63
    folios
    -0.61
    iff
    -0.61
    POSITIVE LOGITS
    etooth
    1.22
    encers
    1.01
    enza
    0.98
    encer
    0.92
    nder
    0.91
    enced
    0.91
    orescent
    0.88
    jah
    0.88
    pton
    0.88
    vre
    0.87
    Activations Density 0.058%

    No Known Activations