© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 24380
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal actions or responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to stigma and social issues surrounding health and human rights

    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
     Pwr
    -0.57
    cffffcc
    -0.55
    undai
    -0.49
    urai
    -0.48
    phies
    -0.47
    )!
    -0.46
    )?
    -0.46
    ³³³³
    -0.45
    amiya
    -0.45
     Died
    -0.43
    POSITIVE LOGITS
     perceived
    0.59
     outcome
    0.53
     impending
    0.52
     outcomes
    0.50
     behav
    0.49
     agenda
    0.48
     inaction
    0.48
     unfolding
    0.47
     attribution
    0.47
     outweigh
    0.47
    Activations Density 3.116%

    No Known Activations