© 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. 11-RES-JB
    11. 20516
    Prev
    Next
    INDEX
    Explanations

    causal relationships or attributions of various issues to specific factors

    oai_token-act-pair · gpt-3.5-turbo

    causal relationships between factors and negative health or environmental outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.92
    displayText
    -0.80
    EStreamFrame
    -0.76
    alan
    -0.75
    ĸļ
    -0.74
    ISO
    -0.72
    FTWARE
    -0.72
    AU
    -0.72
    idav
    -0.71
    Statement
    -0.71
    POSITIVE LOGITS
     poverty
    1.16
     deaths
    1.14
     crime
    1.13
     diseases
    1.13
     cancers
    1.08
     criminality
    1.07
     illnesses
    1.04
     cancer
    1.03
     impover
    1.01
     murders
    1.01
    Activations Density 0.331%

    No Known Activations