© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 7034
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially ones related to locations

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to locations, organizations, and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lahoma
    -0.82
    atron
    -0.82
    lyn
    -0.82
    gee
    -0.81
    yt
    -0.81
    orer
    -0.80
    obia
    -0.80
    apo
    -0.79
    osate
    -0.78
    ington
    -0.78
    POSITIVE LOGITS
    TERN
    1.37
    ENSE
    1.21
    ER
    1.20
    ISTER
    1.19
    ANCE
    1.18
    INT
    1.15
    VEN
    1.15
    WAYS
    1.15
    REC
    1.15
    MENT
    1.14
    Activations Density 0.035%

    No Known Activations