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. 4-RES-JB
    6. 12638
    Prev
    Next
    INDEX
    Explanations

    the word "Allah" at varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Abbas."

    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
     insured
    -0.73
     paycheck
    -0.73
     Colossus
    -0.71
     disse
    -0.69
     Pengu
    -0.69
     glim
    -0.69
     mammal
    -0.68
     unden
    -0.66
     ancest
    -0.64
     hemor
    -0.64
    POSITIVE LOGITS
    renheit
    1.41
    aha
    1.10
    awk
    1.03
    abad
    1.02
    ibi
    1.01
    olics
    1.00
    tml
    0.98
    ttp
    0.98
    abil
    0.97
    aban
    0.96
    Activations Density 0.013%

    No Known Activations