© 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. 7-RES-JB
    11. 19219
    Prev
    Next
    INDEX
    Explanations

    words related to negativity or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.81
     periodically
    -0.72
    bush
    -0.69
     accordingly
    -0.66
    =#
    -0.66
     fixme
    -0.65
     whenever
    -0.65
     respectfully
    -0.65
    cember
    -0.64
    çĭ
    -0.62
    POSITIVE LOGITS
     slightest
    1.41
     usual
    1.11
     brightest
    1.01
     same
    1.00
     easiest
    0.95
     smartest
    0.94
     happiest
    0.82
     nor
    0.81
     greatest
    0.80
     smallest
    0.80
    Activations Density 0.082%

    No Known Activations