© 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. 24383
    Prev
    Next
    INDEX
    Explanations

    phrases related to political leanings and affiliations

    oai_token-act-pair · gpt-3.5-turbo

    references to left-wing political ideologies and groups

    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
     Pell
    -0.74
     Prol
    -0.72
     patience
    -0.67
     visitation
    -0.63
     Mahjong
    -0.63
     Letters
    -0.62
    ulhu
    -0.61
     predic
    -0.60
     Solitaire
    -0.60
     Flavoring
    -0.59
    POSITIVE LOGITS
    leaning
    1.50
    wing
    1.40
    hander
    1.36
    handed
    1.35
    brain
    1.33
    sided
    1.27
    footed
    1.22
    liberal
    1.21
    behind
    1.15
    overs
    1.14
    Activations Density 0.034%

    No Known Activations