© 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. 22318
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to intense anger or strong emotions like fury

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "furious" and its variations indicating strong anger or frustration

    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
    •layer 0 - anger

    No Comments

    Negative Logits
    sa
    -0.81
    oga
    -0.79
    ach
    -0.79
    STEM
    -0.76
    wcsstore
    -0.75
     è£ıè
    -0.70
    sg
    -0.64
    acho
    -0.64
    ø
    -0.63
     Measure
    -0.63
    POSITIVE LOGITS
     furious
    3.47
     fury
    2.22
     frantic
    2.00
     Furious
    1.95
     enraged
    1.68
     furiously
    1.66
     fren
    1.64
     ferocious
    1.58
     infuri
    1.55
     outraged
    1.43
    Activations Density 0.043%

    No Known Activations