© 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. 9-RES-JB
    11. 15536
    Prev
    Next
    INDEX
    Explanations

    phrases that express strong opinions or evaluations, often using words like "hard," "better," "good," "open," "well," "sick," "welcome," "prepared," and "advised."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating difficulty or challenges in achieving something

    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
     innocuous
    -0.67
     deform
    -0.65
     succession
    -0.64
    ulence
    -0.62
     separat
    -0.62
     combustion
    -0.61
     intimacy
    -0.61
    geries
    -0.60
     unrem
    -0.60
     Combine
    -0.59
    POSITIVE LOGITS
     aware
    1.09
     pleased
    1.09
    cerned
    1.09
     interested
    1.02
     willing
    1.01
    aware
    0.98
     obliged
    0.98
     convinced
    0.97
    interested
    0.96
     delighted
    0.96
    Activations Density 0.469%

    No Known Activations