Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21312
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideologies, particularly socialism and Marxism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political ideologies, particularly socialist and Marxist concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourcing
    -0.90
    trak
    -0.86
    Downloadha
    -0.86
    iard
    -0.82
    emis
    -0.82
     Drawn
    -0.81
    tesy
    -0.80
    urers
    -0.79
    ickle
    -0.77
    ources
    -0.77
    POSITIVE LOGITS
     tendencies
    1.08
     strongh
    0.98
     tracts
    0.97
     ideals
    0.96
     stronghold
    0.94
     zeal
    0.94
     enclave
    0.93
     movement
    0.92
     movements
    0.92
     ide
    0.90
    Activations Density 0.091%

    No Known Activations