Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17437
    Prev
    Next
    INDEX
    Explanations

    sentences that give advice or instructions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that provide insights or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sovereignty
    -0.78
     millenn
    -0.77
     unmanned
    -0.74
     birthplace
    -0.73
     disemb
    -0.73
     alleged
    -0.73
     unbeaten
    -0.72
     savage
    -0.71
     waged
    -0.71
     unaccount
    -0.71
    POSITIVE LOGITS
     Alternatively
    1.60
     Depending
    1.59
     Especially
    1.56
     Otherwise
    1.49
     Usually
    1.49
     Besides
    1.45
     Likewise
    1.45
     Luckily
    1.45
     Ideally
    1.44
     Fortunately
    1.42
    Activations Density 0.460%

    No Known Activations