© 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. 10-RES-JB
    11. 2666
    Prev
    Next
    INDEX
    Explanations

    phrases related to the actions and responsibilities of government

    oai_token-act-pair · gpt-3.5-turbo

    references to government actions and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compat
    -0.72
     wounding
    -0.68
     teammates
    -0.67
     comrades
    -0.66
     teammate
    -0.66
     Wand
    -0.66
     die
    -0.63
     acquaintances
    -0.62
     classmates
    -0.61
    die
    -0.61
    POSITIVE LOGITS
     jurisdiction
    1.12
     reimb
    1.08
     mandated
    1.07
     intervene
    1.05
     promul
    1.04
     legisl
    1.03
     subsid
    1.02
     regulate
    1.01
     declass
    1.01
     enforce
    1.00
    Activations Density 0.430%

    No Known Activations