© 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. 9-RES-JB
    11. 17495
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison and analysis

    oai_token-act-pair · gpt-3.5-turbo

    instances of comparison

    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
    oÄŁ
    -0.82
    vous
    -0.74
    arse
    -0.70
    soever
    -0.67
    achment
    -0.66
    FORE
    -0.65
    dar
    -0.65
    Interstitial
    -0.64
    gren
    -0.64
     havoc
    -0.64
    POSITIVE LOGITS
     apples
    1.20
     favorably
    1.13
     sexes
    0.85
     between
    0.78
     favour
    0.77
     notes
    0.73
     dots
    0.72
     pairs
    0.71
     Compare
    0.70
     eras
    0.69
    Activations Density 0.048%

    No Known Activations