© 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. 8-RES-JB
    11. 22577
    Prev
    Next
    INDEX
    Explanations

    phrases related to internships and international programs

    oai_token-act-pair · gpt-3.5-turbo

    references to internships and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arma
    -0.65
    âĢ¢âĢ¢
    -0.64
     palms
    -0.64
    gger
    -0.63
    âĵĺ
    -0.62
    BR
    -0.62
    Reply
    -0.61
     Gamble
    -0.60
     è£ıè¦ļéĨĴ
    -0.60
    lower
    -0.60
    POSITIVE LOGITS
    ships
    1.50
    ationally
    1.17
    ship
    1.10
    elong
    0.96
    rador
    0.92
    ials
    0.90
    ational
    0.86
    antically
    0.85
    atural
    0.84
    stadt
    0.84
    Activations Density 0.025%

    No Known Activations