© 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. 4-RES-JB
    11. 15237
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Assange"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Julian Assange

    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
    FU
    -0.76
    tml
    -0.71
    relation
    -0.69
    atility
    -0.69
    PATH
    -0.69
    onder
    -0.66
    uns
    -0.64
    PASS
    -0.64
    olina
    -0.61
    namese
    -0.61
    POSITIVE LOGITS
     Assange
    1.19
    ovic
    0.92
    Leaks
    0.85
    ileaks
    0.84
    ylum
    0.82
     WikiLeaks
    0.75
    emouth
    0.75
    quist
    0.75
    minster
    0.74
    abad
    0.73
    Activations Density 0.009%

    No Known Activations