© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 14066
    Prev
    Next
    INDEX
    Explanations

    phrases related to numerical change and increase or decrease

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating changes in numbers or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbn
    -0.83
    ovie
    -0.72
    ndra
    -0.66
    ranch
    -0.66
    urus
    -0.65
    etary
    -0.65
    earable
    -0.65
    à©
    -0.61
    rosso
    -0.61
    Products
    -0.60
    POSITIVE LOGITS
     dramatically
    0.95
     considerably
    0.94
     exponentially
    0.94
     drastically
    0.91
     accordingly
    0.90
     sharply
    0.88
     substantially
    0.86
     significantly
    0.86
     astron
    0.84
     steadily
    0.84
    Activations Density 0.150%

    No Known Activations