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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 10199
    Prev
    Next
    INDEX
    Explanations

    RNA-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of RNA and their related functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥī
    -0.81
     Papua
    -0.79
     Peters
    -0.72
     Ange
    -0.71
     chests
    -0.69
     Gaul
    -0.68
    itution
    -0.67
     Warner
    -0.67
    ãĥ³
    -0.67
    ãĥĥãĥĪ
    -0.66
    POSITIVE LOGITS
    seq
    0.96
     mosqu
    0.92
     challeng
    0.89
    yip
    0.87
    VIDIA
    0.85
    accompan
    0.85
    DAQ
    0.84
     satell
    0.82
    daq
    0.81
    ntil
    0.80
    Activations Density 0.009%

    No Known Activations