© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 10279
    Prev
    Next
    INDEX
    Explanations

    verbs or nouns related to obstructing or hindering something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "blocking."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nice
    -0.85
     Springs
    -0.73
    vm
    -0.70
    conom
    -0.69
    essors
    -0.69
    enture
    -0.68
    Ann
    -0.66
    sis
    -0.66
    gow
    -0.65
    ivil
    -0.65
    POSITIVE LOGITS
     blocking
    1.16
    blocking
    1.13
     blockers
    1.09
     blocker
    0.89
     blockade
    0.81
     inhibitor
    0.78
     inhibitors
    0.73
     inhibition
    0.70
     obstruct
    0.69
     filib
    0.69
    Activations Density 0.006%

    No Known Activations