© 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. 1-RES-JB
    11. 3338
    Prev
    Next
    INDEX
    Explanations

    words related to specific groups of people or professionals

    oai_token-act-pair · gpt-3.5-turbo

    groups or entities involved in movements or causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĦ
    -0.77
     vain
    -0.70
     gent
    -0.69
    buck
    -0.67
     transit
    -0.65
    fur
    -0.64
    âĪĴ
    -0.64
     life
    -0.62
    èª
    -0.61
     present
    -0.59
    POSITIVE LOGITS
     Definition
    1.12
     Called
    1.12
     Characters
    1.03
     Costs
    1.02
     Associ
    1.01
     Serving
    1.00
     Rooms
    1.00
     Dates
    0.98
     Leaders
    0.98
     Differences
    0.98
    Activations Density 0.054%

    No Known Activations