© 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. 7-RES-JB
    11. 18858
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "new" combined with words signaling advancement or improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include various forms of the word "new."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHIP
    -0.74
     NETWORK
    -0.68
    eph
    -0.66
    argon
    -0.66
     Cyrus
    -0.65
    hoe
    -0.64
    ashtra
    -0.64
    ãĤ¡
    -0.63
    vana
    -0.63
    lycer
    -0.62
    POSITIVE LOGITS
     refreshed
    0.84
     inexperienced
    0.84
     unfamiliar
    0.84
     exciting
    0.82
     unexpl
    0.82
    leans
    0.81
     renovated
    0.80
     shiny
    0.80
     unforeseen
    0.80
     improved
    0.77
    Activations Density 0.122%

    No Known Activations