© 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. 3-RES-JB
    11. 3475
    Prev
    Next
    INDEX
    Explanations

    the verb "have" followed by a numeric value indicating a future plan or action

    oai_token-act-pair · gpt-3.5-turbo

    frequent occurrences of the word "have" and related phrases indicating possession or necessity

    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
    é¾įå¥ij士
    -0.67
    athi
    -0.66
     Must
    -0.65
    ixties
    -0.62
    Must
    -0.61
     fearing
    -0.61
    advertisement
    -0.61
    het
    -0.60
    reated
    -0.59
    assing
    -0.59
    POSITIVE LOGITS
     tomorrow
    0.81
     hereafter
    0.80
    ahime
    0.78
    Ĥ¬
    0.74
     someday
    0.74
    wagen
    0.70
    aughters
    0.70
    erto
    0.69
     forever
    0.67
    ADRA
    0.65
    Activations Density 0.409%

    No Known Activations