© 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. 10-RES-JB
    11. 6592
    Prev
    Next
    INDEX
    Explanations

    texts about self-improvement and resilience

    oai_token-act-pair · gpt-3.5-turbo

    expressions of vulnerability and resilience in the face of societal judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    audi
    -0.69
    ItemTracker
    -0.64
     Deadline
    -0.64
    interstitial
    -0.63
    everal
    -0.63
    affe
    -0.61
    atform
    -0.60
    ullivan
    -0.60
    encer
    -0.59
    uscript
    -0.59
    POSITIVE LOGITS
     oppress
    1.26
     injust
    1.22
     ensl
    1.19
     oppression
    1.17
     injustice
    1.15
     oppressed
    1.13
     THEIR
    1.08
     sinful
    1.08
     selfish
    1.08
     immoral
    1.07
    Activations Density 0.902%

    No Known Activations