© 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. 0-RES-JB
    11. 11318
    Prev
    Next
    INDEX
    Explanations

    verbs related to causing harm or negative impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being spared or harmed in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Evolution
    -0.64
     stale
    -0.64
     Rowe
    -0.63
     aggregate
    -0.63
     explo
    -0.61
     Analytics
    -0.60
     Register
    -0.59
    LECT
    -0.59
    Sing
    -0.59
    Fill
    -0.58
    POSITIVE LOGITS
     spared
    3.83
     sparing
    1.81
     spare
    1.38
     unaffected
    1.01
     pard
    0.98
     harmed
    0.87
    orah
    0.87
     Winchester
    0.85
     shielded
    0.81
    hyde
    0.77
    Activations Density 0.033%

    No Known Activations