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. 8-RES-JB
    6. 1394
    Prev
    Next
    INDEX
    Explanations

    political terms and phrases related to power dynamics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote exploitation and critique of capitalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     landmark
    -0.72
     longitudinal
    -0.69
     milestone
    -0.66
     requested
    -0.66
     visually
    -0.63
     Guinness
    -0.62
     optionally
    -0.62
     challeng
    -0.62
     Takeru
    -0.61
     critically
    -0.61
    POSITIVE LOGITS
    polit
    1.07
    ophob
    1.04
    ocrats
    1.01
    ablishment
    0.99
    ocr
    0.96
     liberals
    0.95
     liberalism
    0.93
     bureaucr
    0.91
    ivism
    0.91
     populism
    0.91
    Activations Density 0.572%

    No Known Activations