© 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. 4-RES-JB
    11. 22613
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing issues or uncertainties

    oai_token-act-pair · gpt-3.5-turbo

    recurring themes of concern and uncertainty 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
    wings
    -0.78
     mosqu
    -0.76
    ournal
    -0.76
     cass
    -0.65
     shoots
    -0.64
    ufact
    -0.62
     Fuck
    -0.61
     walks
    -0.61
     Milky
    -0.61
     sidx
    -0.60
    POSITIVE LOGITS
    ģ«
    0.90
     abound
    0.84
    ŃĶ
    0.76
     warranted
    0.75
     undone
    0.72
     hampered
    0.71
    ©¶æ
    0.70
     Corker
    0.69
     moot
    0.69
     overcome
    0.69
    Activations Density 0.891%

    No Known Activations