© 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. 17420
    Prev
    Next
    INDEX
    Explanations

    strings of numbers with a specific format, likely referring to technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values or specifications

    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
     tremend
    -0.94
    olicy
    -0.84
    awaru
    -0.84
    isode
    -0.82
    atem
    -0.82
    enhagen
    -0.81
    atre
    -0.79
    uppet
    -0.79
    andise
    -0.78
    ĺħ
    -0.77
    POSITIVE LOGITS
    384
    1.30
    6666
    1.15
    th
    0.98
    eenth
    0.89
    07
    0.87
    66666666
    0.85
    09
    0.84
    340
    0.84
    37
    0.84
    66
    0.82
    Activations Density 0.027%

    No Known Activations