Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14263
    Prev
    Next
    INDEX
    Explanations

    phrases related to being the center of attention or discussion

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to subjects of interest and debate

    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
    hing
    -0.72
     behaved
    -0.68
     Components
    -0.66
    ITH
    -0.65
    hes
    -0.62
    ents
    -0.61
     basics
    -0.60
     Levels
    -0.60
     aboard
    -0.59
    frog
    -0.59
    POSITIVE LOGITS
     ridicule
    1.12
     intense
    1.00
     ire
    0.99
     scorn
    0.96
     contention
    0.91
     fierce
    0.91
     controversy
    0.90
     scrutiny
    0.90
    ENTION
    0.90
     attention
    0.89
    Activations Density 0.095%

    No Known Activations