© 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. 0-RES-JB
    11. 22355
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a negative outcome or hardship being experienced

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "suffer" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cop
    -0.71
    tool
    -0.70
    ocal
    -0.65
    pool
    -0.65
    kb
    -0.63
     BG
    -0.62
     Authorization
    -0.62
    tml
    -0.62
     Update
    -0.60
     Pos
    -0.60
    POSITIVE LOGITS
     suffer
    3.44
     suffers
    2.34
     suffering
    1.97
     suffered
    1.84
     endure
    1.53
     perish
    1.38
     succumb
    1.37
     deterior
    1.37
     undergo
    1.32
     incur
    1.29
    Activations Density 0.020%

    No Known Activations