© 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. 11-RES-JB
    11. 3536
    Prev
    Next
    INDEX
    Explanations

    the name "Ell" with variations in the following characters

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, likely in connection with media, associations, or events

    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
     visually
    -0.64
     Anthem
    -0.64
    Quotes
    -0.60
    âĸº
    -0.60
    ========
    -0.60
    CHAR
    -0.58
    SHIP
    -0.57
     pump
    -0.57
     chant
    -0.56
     Inferno
    -0.55
    POSITIVE LOGITS
    sworth
    1.37
    ipt
    1.35
    iot
    1.18
    iots
    1.14
    igible
    1.12
    ips
    1.07
    izabeth
    1.04
    abor
    0.99
    igent
    0.97
    icter
    0.95
    Activations Density 0.045%

    No Known Activations