© 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. 12693
    Prev
    Next
    INDEX
    Explanations

    examples of similarity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "similar" across various contexts

    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
    OST
    -0.82
    arden
    -0.72
    uay
    -0.69
    oway
    -0.69
    olate
    -0.69
    ë
    -0.67
    arest
    -0.67
    ole
    -0.67
    ARD
    -0.65
     Loaded
    -0.65
    POSITIVE LOGITS
    lihood
    1.04
    minded
    1.02
     minded
    1.01
     amounts
    0.97
     vein
    0.93
    quartered
    0.93
    worldly
    0.93
     sized
    0.88
     twins
    0.81
    etheless
    0.79
    Activations Density 0.023%

    No Known Activations