© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21823
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong emotional experiences, especially fear, pain, and visceral sensations

    oai_token-act-pair · gpt-3.5-turbo

    emotions and intense physical sensations associated with fear or pain

    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
     Oversight
    -0.87
    olicy
    -0.84
     Cosponsors
    -0.81
     Founding
    -0.80
     Contracts
    -0.78
     Articles
    -0.78
     Infrastructure
    -0.78
     Investments
    -0.77
     Forbes
    -0.74
     Funding
    -0.74
    POSITIVE LOGITS
     palpable
    1.28
     contagious
    1.23
     unbearable
    1.23
     intox
    1.21
     overpower
    1.15
     throb
    1.14
     calming
    1.12
     audible
    1.10
     numb
    1.09
     soothing
    1.09
    Activations Density 0.399%

    No Known Activations