© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2444
    Prev
    Next
    INDEX
    Explanations

    words related to significant transformations or life-changing events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "changing" and its variants

    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
    Not in Any Lists

    No Comments

    Negative Logits
     strongly
    -0.64
     scores
    -0.62
     score
    -0.62
     scored
    -0.61
     ad
    -0.59
     stock
    -0.58
     Factory
    -0.56
     Pro
    -0.55
     Home
    -0.55
     Abbey
    -0.54
    POSITIVE LOGITS
    changing
    3.76
    changes
    2.35
    change
    2.29
    changed
    2.18
    Changing
    2.00
     Changing
    1.66
     changing
    1.65
    moving
    1.39
    saving
    1.34
     altering
    1.29
    Activations Density 0.010%

    No Known Activations