© 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. 4-RES-JB
    11. 570
    Prev
    Next
    INDEX
    Explanations

    words related to beds

    oai_token-act-pair · gpt-3.5-turbo

    references to "bed" in various contexts

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

    No Comments

    Negative Logits
    £ı
    -0.96
    vernment
    -0.83
    İĭ
    -0.81
    auga
    -0.75
    rencies
    -0.68
    iferation
    -0.67
    phies
    -0.66
    aminer
    -0.66
    ãĥ£
    -0.64
    ĨĴ
    -0.64
    POSITIVE LOGITS
    ding
    1.33
    ded
    1.08
    ridden
    1.01
    room
    0.99
    stead
    0.95
    rock
    0.94
    spread
    0.94
    side
    0.93
    urn
    0.91
    lam
    0.91
    Activations Density 0.013%

    No Known Activations