© 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. 11132
    Prev
    Next
    INDEX
    Explanations

    adverbs that indicate a significant change or impact

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dramatically."

    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
    tein
    -0.81
    nar
    -0.71
    nan
    -0.70
    Sem
    -0.70
    icular
    -0.66
    allas
    -0.66
    ansas
    -0.64
    Ô
    -0.64
     intentions
    -0.63
    standing
    -0.63
    POSITIVE LOGITS
     dramatically
    0.82
     proport
    0.74
     deterior
    0.73
     accelerate
    0.73
     soar
    0.72
     sped
    0.71
     drastically
    0.70
     skyrocket
    0.69
    Introduced
    0.69
     impacting
    0.68
    Activations Density 0.011%

    No Known Activations