© 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. 3-RES-JB
    11. 10697
    Prev
    Next
    INDEX
    Explanations

    the word "Got" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Got" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.78
    SPONSORED
    -0.67
    advertisement
    -0.67
    ently
    -0.64
    ively
    -0.60
     governing
    -0.59
    elled
    -0.59
     cooker
    -0.58
     contemplated
    -0.56
    desc
    -0.56
    POSITIVE LOGITS
    cha
    1.05
    terson
    0.93
    istical
    0.91
    ãĤ¤ãĥĪ
    0.88
    ãĥ³ãĤ¸
    0.88
    glers
    0.80
    hers
    0.79
    ãĤ´ãĥ³
    0.77
    nir
    0.77
     Married
    0.77
    Activations Density 0.010%

    No Known Activations