© 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. 9-RES-JB
    11. 1793
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental pollution and regulation

    oai_token-act-pair · gpt-3.5-turbo

    information related to public health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     innocence
    -0.78
    pload
    -0.68
    abal
    -0.66
    lit
    -0.62
    keye
    -0.61
    Reloaded
    -0.61
     Pengu
    -0.61
    Sov
    -0.60
     underdog
    -0.60
     Kop
    -0.59
    POSITIVE LOGITS
    ¶
    0.90
     (%)
    0.86
     ·
    0.85
    ↵↵
    0.83
     âĵĺ
    0.83
     shall
    0.80
     âĢº
    0.79
    ↵
    0.78
     Includes
    0.78
     comprise
    0.76
    Activations Density 0.607%

    No Known Activations