© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 308
    Prev
    Next
    INDEX
    Explanations

    tech-related words and phrases, such as coding frameworks, software tools, and abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    components of a list or items of interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inflic
    -0.77
     disapprove
    -0.68
     wield
    -0.67
     inflict
    -0.65
    azeera
    -0.62
     extrad
    -0.61
     mortal
    -0.58
     nonviolent
    -0.58
     solitary
    -0.58
     occupies
    -0.57
    POSITIVE LOGITS
    sequently
    1.01
     Turns
    0.99
    Luckily
    0.92
     Luckily
    0.91
    Thankfully
    0.87
     luckily
    0.86
     Thankfully
    0.86
    RESULTS
    0.83
    Fortunately
    0.82
    Initially
    0.81
    Activations Density 0.704%

    No Known Activations