© 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. 4-RES-JB
    6. 4110
    Prev
    Next
    INDEX
    Explanations

    names related to professional athletes

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named "Brun" and "Ivins" in the context of an investigation or medical case

    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
    osit
    -0.68
    Ec
    -0.67
     punch
    -0.66
    wards
    -0.65
     vomit
    -0.61
     sunshine
    -0.61
     reinforcement
    -0.60
    fulness
    -0.60
     sidx
    -0.59
    warm
    -0.59
    POSITIVE LOGITS
    ault
    0.84
    ancies
    0.82
    ishers
    0.79
    aults
    0.78
    raud
    0.77
    isher
    0.75
    sonian
    0.75
    icult
    0.75
    aldi
    0.74
    orius
    0.72
    Activations Density 0.031%

    No Known Activations