© 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. 0-RES-JB
    11. 1148
    Prev
    Next
    INDEX
    Explanations

    the word "Ever" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "Ever" in various contexts

    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
     rotate
    -0.71
    Condition
    -0.67
     subsystem
    -0.66
    clock
    -0.62
    Applications
    -0.60
     vary
    -0.60
    Sa
    -0.60
    RECT
    -0.59
    nosis
    -0.59
    root
    -0.59
    POSITIVE LOGITS
     Ever
    3.93
     EVER
    2.35
     ever
    1.86
    Ever
    1.81
    ever
    1.57
     Never
    1.36
     Forever
    1.26
     Know
    0.95
     Always
    0.91
     Yet
    0.90
    Activations Density 0.020%

    No Known Activations