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

    Neuronpedia

    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. 8-RES-JB
    11. 7054
    Prev
    Next
    INDEX
    Explanations

    a specific pattern of characters that are repeated in multiple sequences

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and concepts related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inki
    -0.70
    istine
    -0.68
    immigrant
    -0.68
     unden
    -0.67
    chuk
    -0.67
    ãĥ¯ãĥ³
    -0.66
    Ïī
    -0.66
    same
    -0.65
    ¾
    -0.64
     challeng
    -0.64
    POSITIVE LOGITS
     Removal
    1.05
     Decay
    1.01
     Detected
    0.98
     Warfare
    0.96
     Description
    0.93
     Analysis
    0.92
     Detection
    0.91
     Profile
    0.90
     Problems
    0.88
     Strategies
    0.88
    Activations Density 0.468%

    No Known Activations