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

    Neuronpedia

    Jacobian LensNEW
    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. 3889
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize or introduce a specific statement or topic

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or string that is frequently repeated in phrases

    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
     Drawn
    -0.82
     vulner
    -0.75
     Antar
    -0.74
     Mobil
    -0.67
     Belfast
    -0.66
     sacrific
    -0.64
     Agric
    -0.64
     Gardens
    -0.63
     ropes
    -0.62
     printers
    -0.60
    POSITIVE LOGITS
    same
    0.96
    ï¸ı
    0.96
    fter
    0.92
    href
    0.91
    ski
    0.89
    Pg
    0.89
    shall
    0.83
    felt
    0.81
    few
    0.80
    mir
    0.79
    Activations Density 0.086%

    No Known Activations