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. 6259
    Prev
    Next
    INDEX
    Explanations

    words related to brain functions and processes, such as memory, nerve cells, neurotransmitters, and cognitive functions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to brain chemistry and its effects on neural function

    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
    rek
    -0.88
    ãĤª
    -0.80
    iversary
    -0.79
    ista
    -0.78
    ãĤ¢ãĥ«
    -0.75
    aughs
    -0.75
    é»Ĵ
    -0.73
     anniversary
    -0.72
     sqor
    -0.72
     Skies
    -0.71
    POSITIVE LOGITS
     enzymes
    0.95
     proteins
    0.91
     neurons
    0.89
     gland
    0.84
     bacteria
    0.82
     metabolism
    0.81
     fungus
    0.80
     glands
    0.80
     physiology
    0.79
    immune
    0.78
    Activations Density 0.415%

    No Known Activations