© 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. 2-RES-JB
    11. 9430
    Prev
    Next
    INDEX
    Explanations

    mentions of policies or research studies related to specific policy initiatives

    oai_token-act-pair · gpt-3.5-turbo

    mentions of policies related to public and marijuana-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.71
    yard
    -0.69
     burg
    -0.69
    issan
    -0.67
    utf
    -0.66
     burnt
    -0.66
    enegger
    -0.65
    holiday
    -0.65
    upon
    -0.65
    âĵĺ
    -0.64
    POSITIVE LOGITS
     Policy
    1.26
     Advisor
    1.05
     Policies
    1.05
     Strategies
    1.04
     Preferences
    1.04
     Advis
    1.03
     Perspect
    1.00
     Analyst
    0.99
     Responsibility
    0.96
     Strategy
    0.92
    Activations Density 0.020%

    No Known Activations