© 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. 16300
    Prev
    Next
    INDEX
    Explanations

    the word "Tango" with different variations

    oai_token-act-pair · gpt-3.5-turbo

    references to "Django," a web framework for Python

    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
     sclerosis
    -0.64
     absence
    -0.64
    abet
    -0.62
    pite
    -0.61
    benefit
    -0.61
     purpose
    -0.60
     practicable
    -0.60
     ancest
    -0.59
     reinforcement
    -0.58
     omission
    -0.58
    POSITIVE LOGITS
    ango
    1.23
     Unch
    1.09
     Lans
    0.82
    vernment
    0.81
    bats
    0.78
     Strait
    0.77
    illes
    0.75
    quit
    0.74
    quist
    0.73
    arella
    0.72
    Activations Density 0.013%

    No Known Activations