© 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. 6-RES-JB
    11. 13501
    Prev
    Next
    INDEX
    Explanations

    initials followed by numerical values

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and specific letters or initials related to names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancies
    -0.72
     partName
    -0.67
    asks
    -0.67
    urrencies
    -0.66
    estyles
    -0.64
    allows
    -0.64
    atures
    -0.64
     tabs
    -0.64
    izont
    -0.63
    ources
    -0.62
    POSITIVE LOGITS
    ccording
    1.03
    pillar
    0.87
    Lago
    0.84
    collar
    0.74
    ©¶æ¥µ
    0.72
    ibi
    0.70
    ļé
    0.70
    zona
    0.67
    ENA
    0.67
    pill
    0.66
    Activations Density 0.060%

    No Known Activations