© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13720
    Prev
    Next
    INDEX
    Explanations

    information related to demographic characteristics and political affiliations

    oai_token-act-pair · gpt-3.5-turbo

    references to political affiliations and demographic statistics

    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
     pestic
    -0.66
    ¬¼
    -0.65
     manufact
    -0.61
     miscon
    -0.61
     horm
    -0.60
     vend
    -0.60
     imperative
    -0.60
     pione
    -0.59
     lockdown
    -0.58
    staking
    -0.57
    POSITIVE LOGITS
     (%
    1.23
     compared
    1.23
     (-
    1.15
     (âĪĴ
    1.11
     surveyed
    1.09
     (.
    1.09
     (+
    1.08
     versus
    1.05
     Percentage
    1.03
     (%)
    1.02
    Activations Density 0.286%

    No Known Activations