© 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. 8-RES-JB
    11. 784
    Prev
    Next
    INDEX
    Explanations

    mentions of negative events or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and health 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
     Learns
    -0.74
    00007
    -0.66
    Recomm
    -0.64
    اÙĦ
    -0.61
    laughs
    -0.58
    needs
    -0.58
     wishes
    -0.57
    ãĤ«
    -0.54
    ktop
    -0.54
    ÃŃn
    -0.54
    POSITIVE LOGITS
     abound
    1.32
     are
    1.19
     vary
    1.18
     were
    1.18
     weren
    1.11
     aren
    1.10
     include
    1.07
     resonate
    1.02
     differ
    1.00
     seem
    0.94
    Activations Density 0.927%

    No Known Activations