© 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. 17179
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental contamination or radiation contamination

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sources of information or contamination

    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
    quote
    -0.80
    faced
    -0.75
    clear
    -0.75
    priority
    -0.74
    inion
    -0.74
    olson
    -0.73
    answer
    -0.72
    Width
    -0.70
    proof
    -0.70
    aqu
    -0.69
    POSITIVE LOGITS
     afar
    1.34
     abroad
    1.01
     whence
    0.95
     scratch
    0.94
     thence
    0.90
     elsewhere
    0.83
     everywhere
    0.82
     inside
    0.81
     anywhere
    0.78
     across
    0.77
    Activations Density 0.198%

    No Known Activations