© 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. 0-RES-JB
    11. 22272
    Prev
    Next
    INDEX
    Explanations

    words containing the substring "iller"

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular individual, likely in a context related to their work or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shib
    -0.66
     Sem
    -0.63
     Tai
    -0.63
    ãģį
    -0.63
     shorts
    -0.61
     unic
    -0.61
     order
    -0.59
     sight
    -0.58
     rabbits
    -0.58
     times
    -0.58
    POSITIVE LOGITS
    iller
    4.80
    illing
    2.11
    illery
    1.83
    illed
    1.83
    ills
    1.77
    ILL
    1.64
    ill
    1.60
    iler
    1.42
    illa
    1.38
    ille
    1.32
    Activations Density 0.010%

    No Known Activations