© 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. 1-RES-JB
    11. 9539
    Prev
    Next
    INDEX
    Explanations

    phrases related to explosive actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "blow" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Austral
    -0.70
    VIS
    -0.69
    abet
    -0.68
    Act
    -0.67
    States
    -0.66
    Children
    -0.65
    responsible
    -0.65
    cal
    -0.65
    heid
    -0.64
    quel
    -0.63
    POSITIVE LOGITS
     blowing
    1.10
     blown
    1.07
     blew
    1.03
     whist
    0.87
     blows
    0.85
    renheit
    0.80
     earthqu
    0.75
    blown
    0.74
    reath
    0.73
     blow
    0.73
    Activations Density 0.006%

    No Known Activations