© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24320
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing a specific quality or attribute to something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply bringing something positive or beneficial

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    avior
    -0.78
    ciation
    -0.72
    cz
    -0.71
    afety
    -0.69
    iott
    -0.66
    axter
    -0.64
     Advertisement
    -0.64
    ï¸
    -0.63
    awei
    -0.62
    Ê
    -0.62
    POSITIVE LOGITS
     proceedings
    0.85
     embattled
    0.77
     humankind
    0.74
    tones
    0.73
     ponder
    0.71
     wearer
    0.67
     otherwise
    0.67
     mankind
    0.66
     wounds
    0.64
     those
    0.64
    Activations Density 0.182%

    No Known Activations