© 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. 6-RES-JB
    11. 9975
    Prev
    Next
    INDEX
    Explanations

    the name "l" with various suffixes following it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'l' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.73
    ãĥ¯ãĥ³
    -0.70
     stoked
    -0.66
    ħĭ
    -0.66
     hemor
    -0.65
     constitu
    -0.64
     spirited
    -0.63
     Debor
    -0.63
    ij士
    -0.63
     Dharma
    -0.62
    POSITIVE LOGITS
    ayers
    1.19
    ateral
    1.11
    oyd
    1.10
    yrics
    1.09
    ibraries
    1.09
    azy
    1.08
    ounge
    1.08
    ifestyle
    1.07
    opez
    1.06
    asso
    1.02
    Activations Density 0.040%

    No Known Activations