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. 8-RES-JB
    6. 19224
    Prev
    Next
    INDEX
    Explanations

    words related to media format types, specifically focusing on Blu-ray technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to Blu-ray and DVD releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ETHOD
    -0.79
     BASE
    -0.69
    @@@@
    -0.67
    ONSORED
    -0.65
     TODAY
    -0.65
     SHARES
    -0.65
    enegger
    -0.64
     Occupations
    -0.64
    atican
    -0.64
     disturbance
    -0.64
    POSITIVE LOGITS
    ray
    1.20
    rays
    0.94
    Ray
    0.91
    nova
    0.84
    eared
    0.82
    sided
    0.82
    eye
    0.81
    series
    0.78
    standard
    0.78
    disc
    0.77
    Activations Density 0.040%

    No Known Activations