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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7-RES-JB
    6. 4260
    Prev
    Next
    INDEX
    Explanations

    the phrase "the idea of" followed by various concepts or subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey the concept of "the idea of" combined with various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.77
    keys
    -0.76
    ï¸ı
    -0.70
    hesis
    -0.69
    ients
    -0.69
    hens
    -0.68
    NBC
    -0.66
    enth
    -0.65
    WF
    -0.65
    far
    -0.65
    POSITIVE LOGITS
     owning
    0.88
     creating
    0.84
     preserving
    0.83
     having
    0.82
     bringing
    0.78
     needing
    0.77
     eliminating
    0.77
     replacing
    0.77
     separating
    0.76
     storing
    0.76
    Activations Density 0.118%

    No Known Activations