© 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. 4393
    Prev
    Next
    INDEX
    Explanations

    references to government departments or organizations related to health and human services

    oai_token-act-pair · gpt-3.5-turbo

    references to health and human services

    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
     Laden
    -0.70
     pacif
    -0.67
    stick
    -0.65
    ÅŁ
    -0.65
    ãĥª
    -0.65
    ettel
    -0.64
     restless
    -0.62
    gran
    -0.62
    proof
    -0.62
    ãĤ¨ãĥ«
    -0.61
    POSITIVE LOGITS
     Services
    1.08
     Provider
    0.99
     Advis
    0.90
     Administration
    0.90
     Provided
    0.89
    ettlement
    0.88
     Advisor
    0.87
     Assistance
    0.86
     Administrator
    0.85
     Agency
    0.84
    Activations Density 0.016%

    No Known Activations