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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3469
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with precise quantities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "just" in various contexts

    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
    hement
    -0.70
    Fact
    -0.58
    amen
    -0.58
    agically
    -0.58
    eli
    -0.57
    esta
    -0.57
    topic
    -0.57
     anytime
    -0.56
    illin
    -0.55
    antis
    -0.55
    POSITIVE LOGITS
    ifiable
    1.04
     shy
    0.98
    ijn
    0.74
    ifications
    0.74
    below
    0.71
     0
    0.67
    ¾
    0.67
     39
    0.66
     marginally
    0.66
     326
    0.66
    Activations Density 0.073%

    No Known Activations