© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1531
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Monte"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Monte" and to a lesser extent, the name "Glen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilk
    -0.76
    terror
    -0.68
     underwear
    -0.67
    Shop
    -0.65
    ulk
    -0.65
    Org
    -0.64
    BUS
    -0.64
     <!--
    -0.64
     objectionable
    -0.64
    KK
    -0.64
    POSITIVE LOGITS
     Monte
    4.13
     Glen
    1.25
     Mont
    1.09
     Uruguay
    1.07
     Monaco
    1.06
     Roche
    1.04
     Mesa
    1.02
    mont
    1.00
     Gord
    1.00
     Loren
    0.99
    Activations Density 0.036%

    No Known Activations