© 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. 17455
    Prev
    Next
    INDEX
    Explanations

    phrases related to identity and self-worth

    oai_token-act-pair · gpt-3.5-turbo

    expressions of self-identity and personal struggle

    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
    pmwiki
    -0.95
     dispatch
    -0.77
     Locations
    -0.75
    osate
    -0.75
     refres
    -0.74
     Topics
    -0.74
    itures
    -0.74
     Utilities
    -0.74
     conclud
    -0.73
     rollout
    -0.73
    POSITIVE LOGITS
     ashamed
    1.19
     born
    1.13
     afraid
    1.09
     gay
    1.08
     oppressed
    1.07
     alive
    1.05
     virtuous
    1.03
     homosexual
    1.00
     invincible
    0.98
     proud
    0.98
    Activations Density 0.325%

    No Known Activations