© 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. 8-RES-JB
    11. 6332
    Prev
    Next
    INDEX
    Explanations

    terms related to various concerns and issues

    oai_token-act-pair · gpt-3.5-turbo

    concerns related to social and economic issues

    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
    enium
    -0.76
    asonic
    -0.69
    strom
    -0.69
    uth
    -0.67
    onz
    -0.65
     Horses
    -0.64
    Publisher
    -0.64
    ength
    -0.62
     Coffin
    -0.62
    Cub
    -0.61
    POSITIVE LOGITS
    hots
    0.98
    priority
    0.98
     hardest
    0.96
     impacted
    0.96
     affected
    0.96
     singled
    0.92
     priority
    0.91
     concern
    0.88
    affected
    0.86
    angered
    0.85
    Activations Density 1.205%

    No Known Activations