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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6655
    Prev
    Next
    INDEX
    Explanations

    references to the abbreviation "Mo" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the mention of 'Mo' as a significant entity, likely related to geographic locations or notable events associated with it

    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
    xual
    -0.81
     ath
    -0.76
    sth
    -0.70
    __
    -0.66
    Ĭ
    -0.64
     binary
    -0.64
     Paragu
    -0.63
    ł
    -0.62
     posit
    -0.62
    izon
    -0.61
    POSITIVE LOGITS
     Mo
    3.65
    Mo
    2.89
     MO
    1.75
     mo
    1.68
     Moose
    1.48
    mo
    1.42
     Fo
    1.34
     Mu
    1.34
     Mog
    1.30
    MO
    1.28
    Activations Density 0.021%

    No Known Activations