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. 0-RES-JB
    6. 23645
    Prev
    Next
    INDEX
    Explanations

    words related to behaviors or concepts related to personal or social responsibility

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "ance" related to agreements, ignorance, and general conditions

    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
     Beg
    -0.68
     widgets
    -0.63
     Wad
    -0.62
     uncom
    -0.59
     tub
    -0.58
     toget
    -0.57
     Uzbek
    -0.56
     graz
    -0.56
     CLIENT
    -0.56
     wal
    -0.55
    POSITIVE LOGITS
    ance
    4.69
    ances
    3.15
    ANCE
    2.89
    ancing
    2.19
    anced
    2.15
    ancers
    1.98
    ANC
    1.91
    ancy
    1.81
    ancer
    1.79
    antly
    1.71
    Activations Density 0.009%

    No Known Activations