© 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. 10-RES-JB
    11. 14016
    Prev
    Next
    INDEX
    Explanations

    terms related to technological advancement and progress

    oai_token-act-pair · gpt-3.5-turbo

    terms related to innovation and technological advancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nee
    -0.67
    oran
    -0.66
    ahan
    -0.66
     Lumpur
    -0.66
    allah
    -0.64
    ãĥĺãĥ©
    -0.63
    thia
    -0.63
     Metatron
    -0.62
    EVA
    -0.62
    ebin
    -0.62
    POSITIVE LOGITS
     innov
    0.97
     incub
    0.97
     innovation
    0.93
     breakthrough
    0.91
     mindset
    0.90
    ously
    0.86
     innovations
    0.82
     accelerator
    0.80
    iveness
    0.79
     entrepreneurship
    0.77
    Activations Density 0.075%

    No Known Activations