© 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. 6-RES-JB
    11. 7968
    Prev
    Next
    INDEX
    Explanations

    words related to technology and computer programming

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to specific terms or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cortex
    -0.72
     arrow
    -0.65
     Swordsman
    -0.64
     flakes
    -0.62
     transmitting
    -0.60
     Gutenberg
    -0.59
     Hilbert
    -0.58
     sourcing
    -0.57
     Pastebin
    -0.57
     blender
    -0.56
    POSITIVE LOGITS
    Magikarp
    0.83
    /-
    0.80
    phia
    0.80
    ãĤ¨ãĥ«
    0.79
    ROR
    0.78
    ifest
    0.76
    igans
    0.73
    PF
    0.70
    pse
    0.68
    ricks
    0.67
    Activations Density 0.269%

    No Known Activations