© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 20690
    Prev
    Next
    INDEX
    Explanations

    words related to rapid success or growth

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to notable achievements or rises in status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parish
    -0.72
     Luxem
    -0.70
     Siem
    -0.69
     Brav
    -0.68
     Republic
    -0.68
    ombat
    -0.65
    kefeller
    -0.63
    fing
    -0.62
    sein
    -0.61
     Bunny
    -0.59
    POSITIVE LOGITS
    ril
    0.94
    ographed
    0.84
    utical
    0.83
    oric
    0.82
    encing
    0.78
    emonic
    0.76
    entially
    0.75
    entials
    0.75
    âĸ¬âĸ¬
    0.74
    anche
    0.74
    Activations Density 0.024%

    No Known Activations