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

    Neuronpedia

    APICircuit 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. 11-RES-JB
    6. 18358
    Prev
    Next
    INDEX
    Explanations

    the word "Cit" or variations of it, such as "Citrix" or "Citigroup"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company Citigroup and related branding references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hopeful
    -0.70
    quickShipAvailable
    -0.67
     attainment
    -0.61
    ãĤĭ
    -0.61
    tty
    -0.60
    Ł
    -0.59
     Hour
    -0.58
    ARDS
    -0.58
     Direction
    -0.57
     stopp
    -0.56
    POSITIVE LOGITS
    igroup
    1.39
    rix
    1.36
    rus
    1.34
    adel
    1.11
    ron
    1.08
    Ec
    1.08
    rine
    1.05
    rate
    1.05
    ronic
    1.04
    ric
    1.04
    Activations Density 0.049%

    No Known Activations