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. 3-RES-JB
    6. 14822
    Prev
    Next
    INDEX
    Explanations

    phrases related to capitalist concepts and ideologies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to capitalism and class struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.90
     Flavoring
    -0.83
    tis
    -0.83
    aukee
    -0.81
    HCR
    -0.78
    boarding
    -0.76
    ctica
    -0.75
    pell
    -0.75
    Pad
    -0.74
    20439
    -0.72
    POSITIVE LOGITS
     capitalist
    0.91
     capitalists
    0.79
     enterprises
    0.77
     bourgeois
    0.73
    rior
    0.69
     dystop
    0.69
    orpor
    0.69
    ourgeois
    0.67
     republic
    0.67
     exploitation
    0.66
    Activations Density 0.019%

    No Known Activations