© 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. 9-RES-JB
    11. 8952
    Prev
    Next
    INDEX
    Explanations

    references to the concept of moving on or progressing to the next stage or chapter

    oai_token-act-pair · gpt-3.5-turbo

    references to sequential events or items, particularly in a narrative or instructional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nered
    -0.86
    ¬¼
    -0.75
    ocker
    -0.72
    76561
    -0.69
    leeve
    -0.68
     recently
    -0.67
    kered
    -0.63
     breached
    -0.63
     Entered
    -0.63
     Changed
    -0.63
    POSITIVE LOGITS
     installments
    0.84
     installment
    0.76
     onwards
    0.69
    govtrack
    0.67
    enium
    0.67
     refres
    0.65
    ologies
    0.64
    Learn
    0.62
    .—
    0.61
    arsity
    0.60
    Activations Density 0.210%

    No Known Activations