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. 9-RES-JB
    6. 10253
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and syntax

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "with" indicating the use or combination of tools or techniques

    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
    insula
    -0.75
    ulet
    -0.74
    oli
    -0.72
    handler
    -0.71
    SPONSORED
    -0.68
    ÄŁ
    -0.68
    jah
    -0.67
    Uk
    -0.66
    Labour
    -0.66
    ãĥī
    -0.66
    POSITIVE LOGITS
    draw
    1.27
     impunity
    1.19
     regard
    1.17
     regards
    1.12
     minimal
    1.10
     respect
    1.09
    stood
    1.05
     hindsight
    1.02
     ease
    0.98
     proper
    0.97
    Activations Density 0.208%

    No Known Activations