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. 4-RES-JB
    6. 22877
    Prev
    Next
    INDEX
    Explanations

    references to characters and elements from the "Twilight" franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to characters and elements from the "My Little Pony" universe

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

    No Comments

    Negative Logits
    ulative
    -0.90
    daq
    -0.77
    irin
    -0.75
    olulu
    -0.75
    enance
    -0.73
    sembly
    -0.73
    raham
    -0.73
    ntil
    -0.69
    Į
    -0.67
    Ĩ
    -0.67
    POSITIVE LOGITS
     Sparkle
    1.67
     Twilight
    1.01
     Imperium
    0.93
     Princess
    0.81
     Spike
    0.80
     Celest
    0.79
     Zone
    0.78
     Struggle
    0.77
    cess
    0.74
    ween
    0.72
    Activations Density 0.017%

    No Known Activations