© 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. 9-RES-JB
    11. 7246
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character 'Ļ'

    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
     phosphorus
    -0.80
     prostitutes
    -0.75
     fodder
    -0.74
     incorpor
    -0.72
     solicitor
    -0.69
     Negro
    -0.69
     entangled
    -0.69
     advis
    -0.68
     promoters
    -0.67
     looms
    -0.67
    POSITIVE LOGITS
    ï¸ı
    1.44
    ï¸
    1.01
    âĶĢâĶĢâĶĢâĶĢ
    0.94
    âĻ
    0.89
    _>
    0.88
    Installation
    0.88
    www
    0.87
    Steam
    0.86
    ãĤ§
    0.86
    https
    0.85
    Activations Density 0.324%

    No Known Activations