© 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. 16692
    Prev
    Next
    INDEX
    Explanations

    negative commentary on political figures and processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political dishonesty and manipulation

    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
     âĨij
    -0.90
    sterdam
    -0.82
     Activities
    -0.78
     Researchers
    -0.75
     TOR
    -0.75
     Annotations
    -0.74
    isoft
    -0.72
     Trave
    -0.70
     [+
    -0.68
    olphins
    -0.68
    POSITIVE LOGITS
     populism
    1.29
     centrist
    1.28
     centr
    1.28
     populist
    1.23
     elector
    1.22
     voters
    1.18
     electorate
    1.18
     conservatism
    1.17
     neocons
    1.14
     electoral
    1.13
    Activations Density 0.745%

    No Known Activations