© 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. 10-RES-JB
    11. 13713
    Prev
    Next
    INDEX
    Explanations

    instances of the word "letter" followed by names of people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "letter" and related phrases about correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptions
    -0.76
    Variable
    -0.71
    react
    -0.66
    Ħ¢
    -0.66
     hybrids
    -0.65
     angle
    -0.65
     possibilities
    -0.65
     havoc
    -0.64
    variable
    -0.63
    illusion
    -0.63
    POSITIVE LOGITS
     letter
    1.28
     addressed
    1.15
     written
    1.14
    signed
    1.12
     dated
    1.11
     letters
    1.11
     penned
    1.07
    letter
    1.07
     signed
    1.06
     urging
    1.05
    Activations Density 0.149%

    No Known Activations