© 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. 2496
    Prev
    Next
    INDEX
    Explanations

    topics or subjects mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a subject of discussion or debate

    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
    yy
    -0.71
    onse
    -0.64
     nephew
    -0.64
     Americas
    -0.61
    arat
    -0.60
     Mex
    -0.60
     behaved
    -0.57
     ok
    -0.57
     prevailed
    -0.56
    hes
    -0.56
    POSITIVE LOGITS
     ridicule
    1.05
    ENTION
    0.96
     ire
    0.95
     scorn
    0.89
    spection
    0.87
     attention
    0.82
     controversy
    0.74
     scrutiny
    0.71
     criticism
    0.71
     jokes
    0.69
    Activations Density 0.160%

    No Known Activations