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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22604
    Prev
    Next
    INDEX
    Explanations

    verbs related to making decisions or taking actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express intentions or goals

    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
     Else
    -0.63
     Canary
    -0.62
     Mens
    -0.61
     Relief
    -0.61
     Pak
    -0.61
     Appropriations
    -0.58
    Plus
    -0.58
     Cosponsors
    -0.58
     casualty
    -0.57
    afety
    -0.57
    POSITIVE LOGITS
     accomplish
    1.15
     emulate
    1.08
     achieve
    1.06
     eradicate
    0.91
     avoid
    0.90
     eliminate
    0.90
     attain
    0.86
     solve
    0.86
     pursue
    0.85
     improve
    0.85
    Activations Density 0.123%

    No Known Activations