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. 6-RES-JB
    6. 21172
    Prev
    Next
    INDEX
    Explanations

    ideologies and belief systems

    oai_token-act-pair · gpt-3.5-turbo

    references to various political and social ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parts
    -0.70
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.68
     Editors
    -0.66
    umm
    -0.63
    vol
    -0.63
     CFR
    -0.63
    abet
    -0.61
    76561
    -0.61
    ãĥīãĥ©
    -0.60
    fman
    -0.60
    POSITIVE LOGITS
    anship
    0.91
    ophobia
    0.85
    ophobic
    0.82
     fuelled
    0.82
     perv
    0.81
    opathy
    0.81
    jriwal
    0.77
    ISM
    0.77
     engulfed
    0.76
    atism
    0.76
    Activations Density 0.084%

    No Known Activations