Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9696
    Prev
    Next
    INDEX
    Explanations

    terms related to right-wing political ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to right-wing politics

    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
    ADRA
    -0.66
     Remastered
    -0.65
     Aires
    -0.65
     Takeru
    -0.64
     Qiao
    -0.64
     Mats
    -0.64
     Guan
    -0.63
    DAQ
    -0.63
     McGee
    -0.61
     PID
    -0.61
    POSITIVE LOGITS
    wing
    1.49
     wing
    1.31
    ists
    1.11
    leaning
    1.10
    Wing
    1.09
     flank
    1.08
    ist
    1.05
    liners
    0.96
    lean
    0.94
    ervative
    0.93
    Activations Density 0.050%

    No Known Activations