© 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. 0-RES-JB
    11. 16812
    Prev
    Next
    INDEX
    Explanations

    keywords related to information processing, such as "processing", "information", "unit", and "logic"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to information processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andals
    -0.83
     vows
    -0.75
     Enemies
    -0.74
     Pants
    -0.71
    fell
    -0.70
    bern
    -0.70
     Playboy
    -0.68
    ampions
    -0.66
    raham
    -0.66
    andem
    -0.65
    POSITIVE LOGITS
     processing
    3.75
     Processing
    2.93
    processing
    2.87
     processed
    2.11
     processors
    2.00
     processor
    1.92
    Process
    1.74
     handling
    1.54
    process
    1.51
     parsing
    1.48
    Activations Density 0.032%

    No Known Activations