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. 11-RES-JB
    6. 4461
    Prev
    Next
    INDEX
    Explanations

    political figures and their actions

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    Roberts
    -1.13
     Robertson
    -1.12
     ATI
    -0.92
     Manziel
    -0.89
     Arpaio
    -0.87
     Barnett
    -0.84
     Carbuncle
    -0.83
     Bundy
    -0.83
     Rangers
    -0.82
     Griffin
    -0.80
    POSITIVE LOGITS
     Schumer
    1.01
    umenthal
    0.93
     Dianne
    0.91
     Vermont
    0.89
     Blumenthal
    0.83
     Minority
    0.82
     Stamford
    0.82
     Feinstein
    0.80
    democratic
    0.79
     Democrat
    0.79
    Activations Density 0.214%

    No Known Activations