© 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. 10-RES-JB
    11. 6719
    Prev
    Next
    INDEX
    Explanations

    phrases related to writing activities or hobbies

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate action or activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.98
    osate
    -0.93
    trak
    -0.89
    ridor
    -0.85
    phia
    -0.82
    è£ħ
    -0.80
    DragonMagazine
    -0.80
    mie
    -0.78
    eday
    -0.73
    oday
    -0.71
    POSITIVE LOGITS
     surprises
    1.22
     disasters
    1.14
     acron
    1.12
     things
    1.10
     crises
    1.08
     narratives
    1.07
     dictators
    1.06
     anecdotes
    1.05
     controversies
    1.04
     announcements
    1.03
    Activations Density 0.669%

    No Known Activations