© 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. 10-RES-JB
    11. 10214
    Prev
    Next
    INDEX
    Explanations

    words related to movements or vibrations

    oai_token-act-pair · gpt-3.5-turbo

    words with specific phonetic patterns, particularly with "ug," "ob," and "agg" sounds

    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
    ODUCT
    -0.68
     Integrity
    -0.68
     Annotations
    -0.67
    ĻĤ
    -0.64
     Palm
    -0.63
    Chan
    -0.62
     Administ
    -0.61
     tert
    -0.61
     Explorer
    -0.61
     Myers
    -0.61
    POSITIVE LOGITS
    geoning
    1.09
    led
    0.96
    bery
    0.96
    ishly
    0.93
    ling
    0.93
    liness
    0.92
    bled
    0.89
    kered
    0.88
    iness
    0.87
    leness
    0.86
    Activations Density 0.101%

    No Known Activations