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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17990
    Prev
    Next
    INDEX
    Explanations

    words related to lightening or making things less intense

    oai_token-act-pair · gpt-3.5-turbo

    words related to brightness or lightness

    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
    article
    -0.69
    è¦ļéĨĴ
    -0.66
    utan
    -0.63
    google
    -0.61
    0002
    -0.61
    ograms
    -0.60
    ublic
    -0.60
     Winchester
    -0.59
    enza
    -0.59
    roma
    -0.58
    POSITIVE LOGITS
     gears
    0.83
     up
    0.81
     tensions
    0.79
     senses
    0.78
     relations
    0.76
     considerably
    0.74
     tyres
    0.74
     palate
    0.72
     fences
    0.71
     tires
    0.70
    Activations Density 0.210%

    No Known Activations