© 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. 4-RES-JB
    11. 19392
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of 'first-ever'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "first-ever"

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

    No Comments

    Negative Logits
     Beir
    -0.79
    cius
    -0.77
     Tray
    -0.75
     Skydragon
    -0.74
     Bullets
    -0.71
     Laos
    -0.68
    lass
    -0.67
    hung
    -0.64
     Yar
    -0.64
     Dise
    -0.64
    POSITIVE LOGITS
    ever
    0.84
    theless
    0.79
     comeback
    0.76
    agher
    0.73
     recorded
    0.71
    lasting
    0.70
     possible
    0.70
     induct
    0.67
    untarily
    0.67
     EVER
    0.67
    Activations Density 0.017%

    No Known Activations