© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 11372
    Prev
    Next
    INDEX
    Explanations

    the word "Lo" with the highest activation value

    oai_token-act-pair · gpt-3.5-turbo

    the recurring mention of the name "Lo."

    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
    ãĥ¥
    -0.73
    aur
    -0.71
    patrick
    -0.70
    ivery
    -0.68
    ahime
    -0.67
    orpor
    -0.66
    ãģĨ
    -0.65
     phosphate
    -0.65
    atomic
    -0.62
    edge
    -0.60
    POSITIVE LOGITS
     Lo
    3.63
    Lo
    2.78
    lo
    1.71
     LO
    1.64
     lo
    1.63
    LO
    1.29
     Ho
    1.26
     Loop
    1.22
     Ro
    1.13
     Lot
    1.10
    Activations Density 0.016%

    No Known Activations