© 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. 2-RES-JB
    6. 4048
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Umbrella"

    oai_token-act-pair · gpt-3.5-turbo

    names or references related to individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     day
    -0.68
    ablishment
    -0.68
     traveller
    -0.64
    BOOK
    -0.62
    ãĥ£
    -0.61
     morbid
    -0.60
     deduction
    -0.60
    goers
    -0.59
     Afghanistan
    -0.59
    ERAL
    -0.58
    POSITIVE LOGITS
    owship
    1.27
    inson
    0.96
    rell
    0.94
    yth
    0.91
    adoes
    0.89
    ius
    0.89
    amental
    0.88
    ateral
    0.87
    ifer
    0.86
    ipt
    0.84
    Activations Density 0.006%

    No Known Activations