© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    6. 21392
    Prev
    Next
    INDEX
    Explanations

    names of people or places ending in "os" and also the word "Nebraska" in longer phrases

    oai_token-act-pair · gpt-3.5-turbo

    names or references related to people and entities

    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
     Edgar
    -0.87
     Dudley
    -0.86
     Brend
    -0.83
     Mandal
    -0.83
     Bedford
    -0.81
     Faust
    -0.79
     Crimson
    -0.79
     Fa
    -0.79
     Mau
    -0.77
     Hamb
    -0.76
    POSITIVE LOGITS
    os
    1.88
    OS
    1.72
    osi
    1.32
    oS
    1.32
    osa
    1.30
    Os
    1.28
    oses
    1.26
    osaurs
    1.25
    osite
    1.24
    osity
    1.21
    Activations Density 0.217%

    No Known Activations