© 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. 20248
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ima" or any part of it, with a strong preference for the complete word

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity named "ima."

    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
    pocket
    -0.83
    draw
    -0.75
    rooms
    -0.74
    shop
    -0.73
    dep
    -0.73
    advertisement
    -0.70
    spe
    -0.67
    sy
    -0.66
    drawn
    -0.65
    know
    -0.65
    POSITIVE LOGITS
    ima
    1.19
     Centauri
    0.85
    ption
    0.85
    phrine
    0.83
    imi
    0.82
    estro
    0.80
    izon
    0.78
    emia
    0.78
    etric
    0.77
    oka
    0.77
    Activations Density 0.005%

    No Known Activations