© 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. 0-RES-JB
    6. 7651
    Prev
    Next
    INDEX
    Explanations

    locations or rooms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of rooms, particularly related to personal or communal spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     athe
    -0.73
     totality
    -0.64
     TER
    -0.59
     AVG
    -0.59
     arter
    -0.59
     righteousness
    -0.59
     prophe
    -0.58
    åĪ
    -0.58
     bounty
    -0.58
     Tay
    -0.57
    POSITIVE LOGITS
    room
    4.67
    rooms
    4.13
    Room
    2.01
     room
    1.87
     Room
    1.72
     rooms
    1.72
     Rooms
    1.45
    houses
    1.31
    house
    1.31
    stairs
    1.23
    Activations Density 0.012%

    No Known Activations