© 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. 7499
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles and headlines

    oai_token-act-pair · gpt-3.5-turbo

    citations and references to news organizations and locations

    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
     Quantum
    -0.71
    ichick
    -0.64
    racuse
    -0.62
     sequels
    -0.62
     multiplication
    -0.61
     bots
    -0.60
     cabinets
    -0.60
    Shape
    -0.59
     Random
    -0.58
     Double
    -0.58
    POSITIVE LOGITS
    MEN
    0.95
     CITY
    0.94
     COUNTY
    0.89
    INESS
    0.89
    heast
    0.85
    VILLE
    0.85
    VIEW
    0.84
    ccording
    0.84
    ORPG
    0.83
    ENG
    0.83
    Activations Density 0.239%

    No Known Activations