© 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. 10976
    Prev
    Next
    INDEX
    Explanations

    mentions of specific countries

    oai_token-act-pair · gpt-3.5-turbo

    the character "ĺ" which appears in various contexts within the text

    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
     adv
    -0.72
     yarn
    -0.72
     pretext
    -0.72
     arguments
    -0.70
     exploits
    -0.69
     tricks
    -0.69
     sacrific
    -0.68
     cog
    -0.68
     implant
    -0.67
     JPEG
    -0.66
    POSITIVE LOGITS
    where
    0.94
    iversary
    0.91
    ember
    0.91
    capital
    0.90
    region
    0.89
    wide
    0.87
    emb
    0.85
    wealth
    0.84
    east
    0.83
    sure
    0.83
    Activations Density 0.180%

    No Known Activations