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. 6235
    Prev
    Next
    INDEX
    Explanations

    terms related to enhancements or improvements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate improvements or enhancements in various contexts

    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
    soDeliveryDate
    -0.79
    metal
    -0.69
    cas
    -0.68
    place
    -0.68
    corn
    -0.67
    76561
    -0.66
    gs
    -0.66
    gren
    -0.66
    Mos
    -0.65
    pper
    -0.63
    POSITIVE LOGITS
    ments
    1.07
     enhancement
    0.95
     enhancements
    0.91
    mble
    0.90
    mentation
    0.88
     confir
    0.85
    anced
    0.84
     enhances
    0.83
     capacities
    0.83
    issance
    0.81
    Activations Density 0.036%

    No Known Activations