© 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. 9378
    Prev
    Next
    INDEX
    Explanations

    proper nouns or acronyms related to news agencies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "IA" acronym and related references

    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
    wcsstore
    -0.82
    aire
    -0.80
    monkey
    -0.74
    ary
    -0.72
    ende
    -0.72
     guiActiveUnfocused
    -0.70
    things
    -0.70
    raint
    -0.69
    belt
    -0.67
     Dragonbound
    -0.67
    POSITIVE LOGITS
    BILITY
    1.25
    BLE
    1.21
    ULT
    1.01
    EA
    0.99
    BILITIES
    0.99
    VA
    0.95
    ACA
    0.95
    zza
    0.91
    LECT
    0.90
    YS
    0.90
    Activations Density 0.006%

    No Known Activations