© 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. 9-RES-JB
    11. 11723
    Prev
    Next
    INDEX
    Explanations

    descriptions related to losing something desirable, such as credibility or faith

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate loss, credibility, or decline in various contexts

    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
     listed
    -0.61
     cowork
    -0.60
     listing
    -0.60
    ospons
    -0.60
     roundup
    -0.59
     Ballard
    -0.58
    oret
    -0.58
     organizer
    -0.57
    cise
    -0.57
    initely
    -0.57
    POSITIVE LOGITS
    polit
    0.95
    warts
    0.91
     amid
    0.85
     politically
    0.74
    ahime
    0.74
    terness
    0.74
     vis
    0.73
     elector
    0.72
     laure
    0.72
    alties
    0.71
    Activations Density 0.402%

    No Known Activations