© 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. 7-RES-JB
    11. 23631
    Prev
    Next
    INDEX
    Explanations

    phrases or terms emphasizing exclusivity or superiority

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "the" in various contexts

    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
    tackle
    -0.84
     respectively
    -0.70
    anon
    -0.67
    iterator
    -0.65
    aways
    -0.65
    multipl
    -0.65
    thood
    -0.65
    =#
    -0.65
     again
    -0.64
    clerosis
    -0.64
    POSITIVE LOGITS
     slightest
    1.06
     simplest
    1.06
     smallest
    1.00
     brav
    0.90
     basics
    0.88
     wealthiest
    0.86
     finest
    0.85
     strongest
    0.84
     essentials
    0.82
     richest
    0.79
    Activations Density 0.079%

    No Known Activations