Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 11098
    Prev
    Next
    INDEX
    Explanations

    oc words or word parts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "culture" or "cultural elements."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.93
    ħĭ
    -0.68
     Dish
    -0.64
     Uriel
    -0.64
     Fraz
    -0.62
     Voyager
    -0.61
     differe
    -0.60
     Hulk
    -0.60
     FW
    -0.59
     Trin
    -0.59
    POSITIVE LOGITS
    entric
    1.36
    hester
    1.27
    kefeller
    1.15
    abulary
    1.06
    ourse
    1.04
    urrencies
    1.04
    ombat
    1.04
    redits
    1.04
    ontent
    1.02
    ritical
    0.98
    Activations Density 0.028%

    No Known Activations