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

    Neuronpedia

    Jacobian LensNEW
    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. 2304
    Prev
    Next
    INDEX
    Explanations

    terms that are encoded/represented in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or notable figures within a socio-political context

    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
    hement
    -0.74
     XIII
    -0.73
     Tag
    -0.70
     Slug
    -0.68
     Krypt
    -0.67
     Lash
    -0.63
     Quartz
    -0.63
     Lug
    -0.62
     glare
    -0.62
     Mechdragon
    -0.62
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    1.06
    ³³³³³³³³
    0.92
    ³³³
    0.89
    rail
    0.87
    bus
    0.85
    shall
    0.81
    ³³³³
    0.81
    à¼
    0.81
    advant
    0.79
    ever
    0.79
    Activations Density 0.173%

    No Known Activations