© 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. 3-RES-JB
    11. 3124
    Prev
    Next
    INDEX
    Explanations

    words related to excavation or extraction activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to human remains or corpses, particularly in the context of exhumation or burial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inki
    -0.71
     aggregation
    -0.66
     shoulders
    -0.64
     weaving
    -0.63
    shapeshifter
    -0.62
    ween
    -0.62
     volunte
    -0.61
     centres
    -0.60
     aggreg
    -0.60
     eng
    -0.60
    POSITIVE LOGITS
    ciating
    1.10
    nces
    0.93
    olitics
    0.84
    ctions
    0.81
    Pacific
    0.79
    rences
    0.76
    Mars
    0.76
    ordinary
    0.76
    ctors
    0.75
    bia
    0.74
    Activations Density 0.104%

    No Known Activations