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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 7685
    Prev
    Next
    INDEX
    Explanations

    phrases related to perseverance and hard work

    oai_token-act-pair · gpt-3.5-turbo

    expressions of determination and focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qqa
    -0.65
    uration
    -0.65
    DX
    -0.65
    chell
    -0.64
    herent
    -0.63
    iannopoulos
    -0.62
    ulla
    -0.59
    س
    -0.59
     Xeon
    -0.58
    uman
    -0.58
    POSITIVE LOGITS
     lest
    1.28
     innovate
    0.96
     minimizing
    0.95
     risking
    0.94
     simplify
    0.88
     defensively
    0.86
     preferably
    0.86
     hoping
    0.86
     fearing
    0.84
     avoiding
    0.83
    Activations Density 0.547%

    No Known Activations