© 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. 3-RES-JB
    11. 4446
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "La" followed by a proper noun

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the term "La" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.95
    lessly
    -0.92
    Ö¼
    -0.85
    PLIED
    -0.82
    ãĥĩãĤ£
    -0.82
    EMENT
    -0.80
    éĹĺ
    -0.74
     sidx
    -0.74
    lessness
    -0.73
    ICLE
    -0.73
    POSITIVE LOGITS
    uren
    0.99
     Marse
    0.97
    vel
    0.94
    TeX
    0.90
    La
    0.85
    isse
    0.84
     Blanc
    0.83
    quire
    0.83
     La
    0.81
    ver
    0.81
    Activations Density 0.010%

    No Known Activations