© 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. 2-RES-JB
    11. 17658
    Prev
    Next
    INDEX
    Explanations

    acronyms related to financial instruments, particularly ETFs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to investment vehicles and network security

    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
    united
    -0.79
    thritis
    -0.76
     Lakes
    -0.73
    printed
    -0.69
    alter
    -0.68
    pell
    -0.68
     marrow
    -0.68
    cler
    -0.67
     Lys
    -0.66
    bra
    -0.66
    POSITIVE LOGITS
    VPN
    1.12
     VPN
    0.89
    atcher
    0.84
     cipher
    0.82
    èĢħ
    0.82
     Browser
    0.80
     vulner
    0.79
    avascript
    0.79
    ILLE
    0.78
    ython
    0.78
    Activations Density 0.008%

    No Known Activations