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. 20146
    Prev
    Next
    INDEX
    Explanations

    references to Ted Cruz and his political activities

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their actions

    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
     inquest
    -0.86
    MH
    -0.84
    ortmund
    -0.83
     MH
    -0.83
     psychiat
    -0.83
     goblins
    -0.82
    ÅĤ
    -0.80
     Albion
    -0.80
    giene
    -0.80
    ĸļ
    -0.80
    POSITIVE LOGITS
     Cruz
    2.63
    Cruz
    2.58
     Rubio
    1.79
     Ted
    1.65
    Ted
    1.60
     Kasich
    1.42
     Santorum
    1.31
     Carson
    1.23
     Coulter
    1.22
    Rub
    1.21
    Activations Density 0.169%

    No Known Activations