© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22711
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "first-ever."

    oai_token-act-pair · gpt-3.5-turbo

    instances of 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
     cancell
    -0.62
     caf
    -0.59
     mob
    -0.58
     gland
    -0.58
     glands
    -0.58
     massage
    -0.58
     availability
    -0.55
     Maid
    -0.55
     Recreation
    -0.55
     tribal
    -0.54
    POSITIVE LOGITS
    ever
    4.93
    soever
    1.84
     EVER
    1.65
    Ever
    1.60
     Ever
    1.37
     ever
    1.35
    ear
    1.13
    theless
    1.10
    VER
    1.08
    never
    1.03
    Activations Density 0.011%

    No Known Activations