© 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. 1601
    Prev
    Next
    INDEX
    Explanations

    specific codes or digits within texts

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and relevant references in various contexts

    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
     drivers
    -0.73
     teens
    -0.67
     Sherlock
    -0.64
    htaking
    -0.63
     lasted
    -0.62
     Sultan
    -0.62
     thro
    -0.62
    ©¶æ
    -0.61
     bee
    -0.59
    emis
    -0.59
    POSITIVE LOGITS
    RAW
    1.01
    Discussion
    0.90
    Acknowled
    0.87
    Usage
    0.86
    Contribut
    0.85
    Examples
    0.84
    values
    0.83
    Conclusion
    0.82
    Appearances
    0.82
    Example
    0.81
    Activations Density 0.150%

    No Known Activations