© 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
    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. 9466
    Prev
    Next
    INDEX
    Explanations

    references to software development with a focus on Android devices

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Android operating system and its versions

    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
    umber
    -0.77
    atures
    -0.75
    swers
    -0.74
    ilts
    -0.73
    oppy
    -0.73
    akening
    -0.73
    soType
    -0.73
    ablishment
    -0.71
    urers
    -0.70
    uilding
    -0.70
    POSITIVE LOGITS
     android
    1.11
    android
    1.06
    awei
    0.87
     Kush
    0.82
    Android
    0.79
     java
    0.73
     Android
    0.70
     wallpaper
    0.70
     ru
    0.70
    beans
    0.70
    Activations Density 0.010%

    No Known Activations