© 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. 11-RES-JB
    11. 10075
    Prev
    Next
    INDEX
    Explanations

    statements related to political figures and their actions

    oai_token-act-pair · gpt-3.5-turbo

    language related to immigration policy and deportation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     presentations
    -0.72
     manoeuv
    -0.70
    eki
    -0.68
    ktop
    -0.66
     CLR
    -0.64
     organis
    -0.64
    assi
    -0.63
     Quarterly
    -0.63
     behaviours
    -0.63
     Interactive
    -0.63
    POSITIVE LOGITS
     deport
    1.07
     rapists
    1.04
    ISIS
    1.04
     amnesty
    1.04
     ISIS
    1.03
     ObamaCare
    1.02
    Hillary
    1.00
     terrorists
    1.00
     deportation
    0.99
    TRUMP
    0.98
    Activations Density 0.611%

    No Known Activations