© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3399
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reassurance or reminder

    oai_token-act-pair · gpt-3.5-turbo

    statements of assurance and reminders about information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.71
    fman
    -0.68
    ictive
    -0.67
    arde
    -0.66
    discrimination
    -0.65
    artifacts
    -0.63
    adesh
    -0.61
    nam
    -0.59
    bage
    -0.59
    imity
    -0.58
    POSITIVE LOGITS
     readers
    1.71
     viewers
    1.56
     listeners
    1.54
     audiences
    1.40
     us
    1.32
     attendees
    1.24
     Readers
    1.17
     consumers
    1.16
     voters
    1.13
     reader
    1.13
    Activations Density 0.330%

    No Known Activations