© 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. 9-RES-JB
    11. 4636
    Prev
    Next
    INDEX
    Explanations

    phrases related to making arguments and presenting cases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating arguments or debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chang
    -0.70
     births
    -0.64
     servicing
    -0.62
    ufact
    -0.61
    chel
    -0.59
    ghai
    -0.59
    ecast
    -0.59
     exch
    -0.59
     teased
    -0.58
     reborn
    -0.58
    POSITIVE LOGITS
     arguments
    1.35
     argument
    1.34
    argument
    1.32
     assertions
    1.31
     assertion
    1.31
     contention
    1.24
     claim
    1.23
     objections
    1.19
     objection
    1.19
    Arg
    1.19
    Activations Density 1.000%

    No Known Activations