© 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
    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. 8236
    Prev
    Next
    INDEX
    Explanations

    phrases related to official statements or announcements

    oai_token-act-pair · gpt-3.5-turbo

    the presence of announcements and statements

    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
    Mods
    -0.76
    Exper
    -0.72
     experimented
    -0.69
    âī
    -0.68
    etsk
    -0.67
    avorite
    -0.66
    apter
    -0.66
    rity
    -0.65
    import
    -0.65
    Gener
    -0.64
    POSITIVE LOGITS
     statement
    1.47
     tweet
    1.13
     telephone
    1.11
     memo
    1.08
     letter
    1.08
     phone
    1.07
     memorandum
    1.04
     nutshell
    1.04
     emailed
    1.03
     press
    1.03
    Activations Density 0.061%

    No Known Activations