© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9184
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sacrifices or trade-offs

    oai_token-act-pair · gpt-3.5-turbo

    phrases highlighting the concept of "expense" relative to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oggles
    -0.77
     overfl
    -0.70
    ecided
    -0.69
    knit
    -0.67
    binding
    -0.65
    ysis
    -0.64
    ortium
    -0.63
    odes
    -0.63
    terday
    -0.62
    inis
    -0.62
    POSITIVE LOGITS
     expense
    0.81
     detriment
    0.76
    ħĭ
    0.75
     altar
    0.73
    «ĺ
    0.71
    hyde
    0.67
     Savage
    0.66
    edia
    0.64
    ãĤ«
    0.64
     disadvantage
    0.64
    Activations Density 0.021%

    No Known Activations