© 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. 10-RES-JB
    11. 20255
    Prev
    Next
    INDEX
    Explanations

    phrases related to importance or criticality

    oai_token-act-pair · gpt-3.5-turbo

    key aspects and elements related to importance or necessity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ateur
    -0.74
     Carbuncle
    -0.70
    flat
    -0.67
     sweats
    -0.66
    shirts
    -0.66
    WithNo
    -0.64
     vomiting
    -0.63
     vomit
    -0.62
    guyen
    -0.62
    uthor
    -0.61
    POSITIVE LOGITS
    important
    1.01
     crucial
    0.98
     underpin
    0.92
     distinguishing
    0.90
     important
    0.85
     pivotal
    0.85
     vital
    0.83
     impacting
    0.82
     determining
    0.82
     importance
    0.82
    Activations Density 0.166%

    No Known Activations