© 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. 9-RES-JB
    11. 4654
    Prev
    Next
    INDEX
    Explanations

    words and symbols that seem to have no clear connection or theme, potentially indicating noise or data corruption

    oai_token-act-pair · gpt-3.5-turbo

    the presence of numerical values, likely related to counts or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appar
    -0.66
     right
    -0.62
     corresponding
    -0.61
    hement
    -0.60
     intervention
    -0.60
     blinded
    -0.60
     ASCII
    -0.60
     NRS
    -0.59
     acquies
    -0.58
     interception
    -0.58
    POSITIVE LOGITS
    Posted
    1.12
    Ü
    0.91
    RAW
    0.90
    Loading
    0.90
    window
    0.86
    Reviewer
    0.80
    LAB
    0.78
    Rating
    0.77
    è¦ļéĨĴ
    0.77
    inav
    0.77
    Activations Density 0.240%

    No Known Activations