© 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. 3-RES-JB
    11. 5125
    Prev
    Next
    INDEX
    Explanations

    specific phrases in Spanish related to construction and development projects

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations or regions

    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
    DragonMagazine
    -0.95
    oresc
    -0.89
    ramid
    -0.87
    NetMessage
    -0.86
    krit
    -0.83
     Flavoring
    -0.82
    ãĤ¤ãĥĪ
    -0.81
    ambers
    -0.77
    ACE
    -0.77
    ORY
    -0.76
    POSITIVE LOGITS
     la
    1.08
     jour
    0.95
    utsche
    0.90
    activate
    0.88
    legate
    0.88
    arest
    0.87
    cember
    0.85
     los
    0.85
     las
    0.84
    uces
    0.84
    Activations Density 0.014%

    No Known Activations