© 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. 4-RES-JB
    11. 15365
    Prev
    Next
    INDEX
    Explanations

    terms related to animated content or projects

    oai_token-act-pair · gpt-3.5-turbo

    words related to animation and animated characters

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

    No Comments

    Negative Logits
     Indies
    -0.68
     Boys
    -0.68
     mark
    -0.66
    holder
    -0.65
    peak
    -0.64
     Benz
    -0.62
     blunt
    -0.62
     Roses
    -0.61
     Mandela
    -0.60
     Biden
    -0.60
    POSITIVE LOGITS
    agus
    1.15
    ators
    1.10
    ator
    1.08
    oji
    1.06
    agi
    1.05
    osity
    1.02
    ations
    0.99
    itives
    0.98
    anche
    0.96
    ating
    0.94
    Activations Density 0.007%

    No Known Activations