© 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. 2-RES-JB
    11. 23265
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "only"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insula
    -0.67
    actionDate
    -0.65
    communication
    -0.63
    align
    -0.62
    idon
    -0.62
    gnu
    -0.60
    )))
    -0.60
     Diablo
    -0.59
    ItemImage
    -0.58
     à¨
    -0.58
    POSITIVE LOGITS
    onso
    0.78
     incidentally
    0.77
     marginally
    0.76
    teen
    0.75
    ices
    0.74
    isons
    0.72
    phies
    0.68
    imation
    0.67
     Memories
    0.67
     Lives
    0.66
    Activations Density 0.048%

    No Known Activations