© 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. 8-RES-JB
    11. 20355
    Prev
    Next
    INDEX
    Explanations

    words related to physical senses, dimensions, and emotions

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or initialisms, particularly those related to specific titles or names

    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
     tremend
    -0.79
    imens
    -0.75
    ADRA
    -0.72
     tert
    -0.71
     occas
    -0.71
     sender
    -0.68
     seiz
    -0.66
     contrace
    -0.64
    ctions
    -0.62
     annexed
    -0.62
    POSITIVE LOGITS
    ings
    1.15
    bread
    1.07
    ingly
    0.95
    horn
    0.94
    ishly
    0.94
    iness
    0.91
    nuts
    0.90
    bones
    0.90
    dropping
    0.89
    grass
    0.89
    Activations Density 0.178%

    No Known Activations