© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 212
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "general" or phrases related to general concepts or statements

    oai_token-act-pair · gpt-3.5-turbo

    references to the general public or general concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hots
    -0.80
    hops
    -0.73
    hemy
    -0.70
    rus
    -0.70
    friends
    -0.70
     Cups
    -0.69
    poon
    -0.68
    INO
    -0.66
    Prof
    -0.66
    uala
    -0.66
    POSITIVE LOGITS
     populace
    1.08
     environment
    1.06
     extent
    1.03
     landscape
    1.03
     assumption
    1.01
     equivalent
    1.00
     basis
    1.00
     universe
    0.98
     population
    0.98
     process
    0.98
    Activations Density 0.316%

    No Known Activations