© 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. 20760
    Prev
    Next
    INDEX
    Explanations

    words related to being free from certain substances or conditions, such as cruelty-free, meat-free, sugar-free, and lead-free

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts associated with being "free" from certain restrictions or elements, especially in the context of food and lifestyle

    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
    ourney
    -0.78
    ENTS
    -0.73
    liam
    -0.70
    RAFT
    -0.68
    ilater
    -0.68
    quickShipAvailable
    -0.68
    emet
    -0.68
    å°Ĩ
    -0.67
    ional
    -0.66
    åĤ
    -0.66
    POSITIVE LOGITS
    bies
    1.29
    zing
    1.13
    zes
    1.05
    ze
    0.99
    zers
    0.97
    zed
    0.94
    bie
    0.81
    ¥µ
    0.79
     zones
    0.78
    zer
    0.77
    Activations Density 0.015%

    No Known Activations