© 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 EvalsExportsinterp-engineNEWAPI 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. 18842
    Prev
    Next
    INDEX
    Explanations

    references to political figures and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political declarations and criticisms of leadership

    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
    theless
    -0.67
    endum
    -0.66
    pmwiki
    -0.65
     subsequ
    -0.64
    Footnote
    -0.62
     afore
    -0.60
     effected
    -0.59
     appell
    -0.59
    ®,
    -0.58
    techn
    -0.58
    POSITIVE LOGITS
     Kavanaugh
    0.82
    æѦ
    0.76
     MORE
    0.75
     }}
    0.69
     Dems
    0.63
    ]}
    0.63
    Virginia
    0.61
    æ©
    0.61
     celeb
    0.60
    ļéĨĴ
    0.60
    Activations Density 0.056%

    No Known Activations