© 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. 1180
    Prev
    Next
    INDEX
    Explanations

    adjectives or adverbs describing the extent or intensity of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate severity or significance regarding conditions or characteristics

    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
     countless
    -0.65
     superiority
    -0.64
     endlessly
    -0.64
     inev
    -0.63
     innumerable
    -0.61
     impossibility
    -0.61
     overwhelming
    -0.61
     unimaginable
    -0.60
    ></
    -0.59
    uther
    -0.58
    POSITIVE LOGITS
    ebted
    0.69
     Dise
    0.68
     among
    0.67
     amongst
    0.65
     suited
    0.65
    zb
    0.64
    ت
    0.64
    Downloadha
    0.63
    20439
    0.63
    uesday
    0.63
    Activations Density 0.194%

    No Known Activations