© 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. 1-RES-JB
    11. 6562
    Prev
    Next
    INDEX
    Explanations

    references to items or concepts with the term "Little" in them

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the term "Little" associated with various contexts or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktop
    -0.77
    ãĥķãĤ©
    -0.75
    NRS
    -0.75
    orial
    -0.74
    inates
    -0.72
    icular
    -0.71
     actionGroup
    -0.71
    ICAN
    -0.69
    ickr
    -0.68
    CRIP
    -0.67
    POSITIVE LOGITS
     Little
    0.92
    Little
    0.89
    pox
    0.81
    finger
    0.81
     Debbie
    0.77
    woods
    0.77
     Brother
    0.76
     Enough
    0.75
     Bit
    0.74
     Miss
    0.74
    Activations Density 0.008%

    No Known Activations