© 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. 9-RES-JB
    11. 15754
    Prev
    Next
    INDEX
    Explanations

    terms related to app development using frameworks like Django and MongoDB

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to software applications and development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcs
    -0.81
     rites
    -0.67
    vernment
    -0.65
     ceremonies
    -0.64
    NetMessage
    -0.63
     Male
    -0.62
    bent
    -0.62
     Rept
    -0.61
     lows
    -0.61
     consolation
    -0.61
    POSITIVE LOGITS
     skelet
    1.05
    builder
    0.93
     builder
    0.92
    stack
    0.88
     dependencies
    0.84
    Builder
    0.82
     startup
    0.81
     library
    0.80
     src
    0.79
     executable
    0.79
    Activations Density 0.159%

    No Known Activations