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. 11-RES-JB
    6. 23647
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intentions or actions taken by companies or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chr
    -0.72
     Tears
    -0.70
     hangs
    -0.66
     Mour
    -0.66
     weeping
    -0.65
    Jose
    -0.65
    lived
    -0.65
    accompanied
    -0.64
     Malk
    -0.62
    Days
    -0.62
    POSITIVE LOGITS
     automate
    1.36
     innovate
    1.35
     regulate
    1.32
     adopt
    1.31
     implement
    1.25
     integrate
    1.22
     legalize
    1.19
     incorporate
    1.19
     embrace
    1.16
     simplify
    1.16
    Activations Density 0.307%

    No Known Activations