© 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. 4-RES-JB
    11. 10256
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "what" followed by an intense or important event or situation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "what" in various contexts

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

    No Comments

    Negative Logits
    jee
    -0.64
     Gamb
    -0.64
    ster
    -0.62
     Emirates
    -0.60
    enburg
    -0.59
     Sao
    -0.59
    xon
    -0.59
    roads
    -0.57
     Plus
    -0.57
     Hills
    -0.56
    POSITIVE LOGITS
    soever
    1.16
     happens
    1.07
     happened
    1.06
     transpired
    0.98
     constitutes
    0.94
     sorts
    0.94
     kinds
    0.94
     happ
    0.90
     constituted
    0.80
     else
    0.79
    Activations Density 0.107%

    No Known Activations