© 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. 11-RES-JB
    11. 21916
    Prev
    Next
    INDEX
    Explanations

    mentions of achievements, accomplishments or exceptional qualities

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that denote something as significant or important

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diminishing
    -0.80
     slowing
    -0.79
     wasting
    -0.78
     messing
    -0.76
     weakening
    -0.75
     hurting
    -0.75
     dwindling
    -0.75
     fading
    -0.74
     worsening
    -0.74
     decreasing
    -0.72
    POSITIVE LOGITS
    ï¸ı
    1.06
    sets
    0.98
    resents
    0.97
    ously
    0.96
    lishes
    0.94
    ulates
    0.92
    s
    0.89
    pires
    0.89
    ships
    0.86
    uates
    0.86
    Activations Density 0.166%

    No Known Activations