© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 1985
    Prev
    Next
    INDEX
    Explanations

    words related to beds and bedding

    oai_token-act-pair · gpt-3.5-turbo

    mentions of beds and related furniture or 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
    £ı
    -0.85
    İĭ
    -0.75
    auga
    -0.74
     Galile
    -0.69
    vernment
    -0.67
    phies
    -0.66
    rencies
    -0.64
    ãĥ£
    -0.59
    opol
    -0.59
     dismissive
    -0.59
    POSITIVE LOGITS
    ding
    1.26
    rock
    1.14
    ridden
    1.11
    ded
    1.05
    lam
    1.04
    stead
    1.01
    room
    0.99
    spread
    0.98
    side
    0.96
    rooms
    0.94
    Activations Density 0.022%

    No Known Activations