© 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. 7560
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative actions and government processes

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative actions and governmental activities

    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
    Afee
    -0.91
     IMAGES
    -0.85
    ãĤ¨ãĥ«
    -0.85
     compan
    -0.80
     weap
    -0.76
    PLIED
    -0.72
     recru
    -0.71
     handlers
    -0.69
    Atl
    -0.69
     competitor
    -0.69
    POSITIVE LOGITS
     adjourn
    1.42
     convened
    1.36
     unanimously
    1.35
     recess
    1.20
     deliber
    1.19
     deliberations
    1.14
     votes
    1.07
     vote
    1.07
     hearings
    1.05
     voted
    1.04
    Activations Density 0.370%

    No Known Activations