© 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. 4-RES-JB
    11. 16687
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

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

    No Comments

    Negative Logits
    Ò
    -0.71
    embed
    -0.71
     Maher
    -0.70
    /
    -0.69
    agger
    -0.66
     Marxism
    -0.65
    leground
    -0.65
     socialism
    -0.65
    Malley
    -0.65
     Kissinger
    -0.65
    POSITIVE LOGITS
     underside
    1.16
     entire
    1.15
     remainder
    1.12
     easiest
    1.12
     smallest
    1.11
     heaviest
    1.11
     lowest
    1.08
     bottom
    1.04
     desired
    1.03
     slightest
    1.03
    Activations Density 0.498%

    No Known Activations