© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 7342
    Prev
    Next
    INDEX
    Explanations

    political and geographic terms related to current events or disputes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant political events or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concess
    -0.66
     mathemat
    -0.57
     reluct
    -0.53
     notor
    -0.51
     multip
    -0.50
     prototyp
    -0.49
     benign
    -0.49
     conditional
    -0.48
    osite
    -0.48
     conscientious
    -0.48
    POSITIVE LOGITS
    ↵Âł
    1.23
    ↵↵
    1.12
    [/
    1.07
    ↵
    1.07
     Posted
    1.04
    "}
    1.03
    )?
    0.98
    .#
    0.97
    .?
    0.97
    "},"
    0.97
    Activations Density 2.561%

    No Known Activations