© 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. 3990
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and political contexts, as well as behaviors emphasizing individual interests over collective interests

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    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
    ikuman
    -0.74
     tyr
    -0.74
    uly
    -0.73
     unstoppable
    -0.71
     metic
    -0.70
     deity
    -0.69
     gobl
    -0.69
     imperson
    -0.69
    oshenko
    -0.68
     purse
    -0.68
    POSITIVE LOGITS
     Flavoring
    1.11
     Additionally
    1.10
     Needless
    1.10
     Nevertheless
    1.09
     Moreover
    1.07
     However
    1.06
     Furthermore
    1.06
     Accordingly
    1.06
     Conversely
    1.06
     Therefore
    1.06
    Activations Density 1.776%

    No Known Activations