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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 15495
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name 'Wel', particularly in the context of various individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Wel" and various forms of the name "elman."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.88
    */(
    -0.75
     Marketable
    -0.69
     theorem
    -0.69
    è¦ļéĨĴ
    -0.68
     civ
    -0.67
    ħĭ
    -0.64
     behav
    -0.63
     Theft
    -0.62
     vol
    -0.62
    POSITIVE LOGITS
    nesday
    1.13
    zel
    1.07
     Wel
    1.03
    ishes
    0.89
    ths
    0.88
    coming
    0.88
    wyn
    0.87
    ty
    0.81
    kowski
    0.81
    retch
    0.80
    Activations Density 0.012%

    No Known Activations