© 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. 11-RES-JB
    11. 578
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative emotions or situations

    oai_token-act-pair · gpt-3.5-turbo

    themes of tension, emotion, and concern in various contexts

    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
     Tycoon
    -0.75
    ECD
    -0.72
    TION
    -0.71
    DT
    -0.64
    TN
    -0.64
    Ctrl
    -0.63
     detrim
    -0.63
    esson
    -0.63
    EVA
    -0.59
    TT
    -0.59
    POSITIVE LOGITS
     ling
    1.27
     persisted
    1.26
     crept
    1.21
     arose
    1.21
     swirl
    1.20
     prevailed
    1.18
     erupted
    1.17
     gripped
    1.16
     raged
    1.16
     persists
    1.15
    Activations Density 0.237%

    No Known Activations