© 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. 1536
    Prev
    Next
    INDEX
    Explanations

    short phrases beginning or ending with quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of quotation marks

    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
     favor
    -0.78
     bunk
    -0.71
     footing
    -0.69
     veget
    -0.68
     mids
    -0.68
     virgin
    -0.68
     ornament
    -0.68
     UX
    -0.66
     honor
    -0.65
     slam
    -0.65
    POSITIVE LOGITS
    Therefore
    1.19
    Whereas
    1.16
    There
    1.14
    It
    1.11
    We
    1.09
    Whoever
    1.09
    Moreover
    1.09
    Fortunately
    1.09
    They
    1.08
    Clearly
    1.07
    Activations Density 0.084%

    No Known Activations