© 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. 0-RES-JB
    11. 15216
    Prev
    Next
    INDEX
    Explanations

    names of places or people ending with "el"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "el."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Journals
    -0.65
     summed
    -0.59
     snatch
    -0.59
     thru
    -0.58
    åħī
    -0.58
    ========
    -0.57
     Timeline
    -0.57
     hours
    -0.55
    ãģ®ç
    -0.55
     Pic
    -0.55
    POSITIVE LOGITS
    el
    4.18
    els
    2.60
    eli
    2.25
    eln
    2.11
    EL
    2.09
    eled
    2.05
    elin
    1.98
    elist
    1.98
    elo
    1.95
    eling
    1.93
    Activations Density 0.021%

    No Known Activations