© 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
    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. 2698
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific name "Julian", particularly focusing on the mention of "Julian Assange"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Julian" and associated 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
    holders
    -0.89
     thirds
    -0.74
    holder
    -0.71
    ittee
    -0.61
    close
    -0.61
    istration
    -0.61
    ributed
    -0.60
    rollers
    -0.59
    astern
    -0.59
    fecture
    -0.59
    POSITIVE LOGITS
     Assange
    1.03
    lectic
    0.73
    sis
    0.73
    iets
    0.72
     Bind
    0.70
     Hacker
    0.69
     Caesar
    0.69
    gins
    0.68
    ian
    0.65
     Abram
    0.64
    Activations Density 0.095%

    No Known Activations