© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 24064
    Prev
    Next
    INDEX
    Explanations

    ranges or values stated in a specific format, often related to statistics or measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ranges or comparisons involving numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.65
    Reviewer
    -0.62
    NetMessage
    -0.61
    auga
    -0.56
    Disclaimer
    -0.55
    Article
    -0.54
    WARE
    -0.53
    Written
    -0.53
    ibilities
    -0.52
    Search
    -0.51
    POSITIVE LOGITS
     5
    1.05
     4
    1.02
     6
    0.99
     10
    0.98
     3
    0.95
     8
    0.95
     15
    0.94
     7
    0.93
     9
    0.93
     35
    0.92
    Activations Density 0.067%

    No Known Activations