© 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. 2662
    Prev
    Next
    INDEX
    Explanations

    programming-related commands and instructions regarding creating or setting up components

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "create" and related actions in a programming context

    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
    abl
    -0.78
    killers
    -0.74
    âĢİ
    -0.74
    AIDS
    -0.73
    anthrop
    -0.73
     airs
    -0.72
    ).[
    -0.71
     Oprah
    -0.70
    Hon
    -0.69
    oft
    -0.68
    POSITIVE LOGITS
     dummy
    1.13
     bunch
    1.00
     standalone
    0.97
     helper
    0.96
     tuple
    0.96
     custom
    0.94
     router
    0.93
     rectangle
    0.93
     user
    0.92
     placeholder
    0.92
    Activations Density 0.290%

    No Known Activations