© 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. 13922
    Prev
    Next
    INDEX
    Explanations

    phrases indicating similarity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    the word "likewise" and variations indicating similarity or comparison

    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
    ü
    -0.70
     Bild
    -0.68
     Stockholm
    -0.63
     Derby
    -0.63
    aceous
    -0.61
    azon
    -0.61
    ender
    -0.60
    ixed
    -0.59
    ene
    -0.59
     RIS
    -0.58
    POSITIVE LOGITS
    etheless
    1.03
    quartered
    0.97
     minded
    0.83
    ctr
    0.79
    theless
    0.79
    æ©Ł
    0.76
     nomine
    0.72
    igible
    0.69
    wise
    0.68
    rius
    0.68
    Activations Density 0.007%

    No Known Activations