© 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. 1-RES-JB
    11. 5578
    Prev
    Next
    INDEX
    Explanations

    the word "omo"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the term "Lomo," likely indicating a focus on a specific product or brand related to instant photography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REAM
    -0.86
    sheet
    -0.77
    writers
    -0.77
    Strike
    -0.70
    dream
    -0.69
    UES
    -0.67
    FUL
    -0.67
    ridges
    -0.64
    staking
    -0.63
    sal
    -0.63
    POSITIVE LOGITS
    omo
    1.61
    ovych
    0.97
    ocy
    0.87
    alogy
    0.86
    ahu
    0.86
    ichi
    0.84
    itus
    0.81
    icho
    0.80
    osexual
    0.79
    iso
    0.76
    Activations Density 0.004%

    No Known Activations