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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9139
    Prev
    Next
    INDEX
    Explanations

    references to various entities or subjects such as "Lion King", "Spider-Man", or "Gotham" that evoke specific pop culture or fictional elements

    oai_token-act-pair · gpt-3.5-turbo

    suffixes that indicate a specific form of nouns or adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.81
    lished
    -0.77
    ÄŁ
    -0.72
     prepar
    -0.71
    ANCE
    -0.70
    Interstitial
    -0.69
    Effective
    -0.66
    ãĥ¼ãĥ³
    -0.66
     completion
    -0.65
     elapsed
    -0.65
    POSITIVE LOGITS
     Squid
    0.97
    fish
    0.85
    hawk
    0.80
    boy
    0.75
    hawks
    0.74
    Squ
    0.72
     Ogre
    0.71
     squid
    0.71
    beard
    0.71
    cube
    0.69
    Activations Density 0.325%

    No Known Activations