© 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. 12-RES-JB
    11. 3972
    Prev
    Next
    INDEX
    Explanations

    phrases related to political support and government actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    political support for military action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     "...
    -1.22
     [...]
    -1.01
     ......
    -0.98
    "...
    -0.96
     -
    -0.91
     ...
    -0.89
     ..."
    -0.88
    ...?
    -0.88
     ....
    -0.86
    ...]
    -0.85
    POSITIVE LOGITS
    ÂŃ
    1.75
    âĢIJ
    0.96
    i
    0.80
    u
    0.79
     ÂŃ
    0.78
    osi
    0.78
    bia
    0.74
    oun
    0.73
    cit
    0.72
    ati
    0.72
    Activations Density 0.036%

    No Known Activations