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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10-RES-JB
    6. 16905
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and negotiations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to expectations and outcomes in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ////////////////
    -0.75
    ãĤ¦ãĤ¹
    -0.73
    ãĤ©
    -0.73
    xxxx
    -0.72
    Liter
    -0.69
    xxx
    -0.68
    *.
    -0.68
    .*
    -0.67
    venth
    -0.67
    gru
    -0.66
    POSITIVE LOGITS
     Corbyn
    1.24
     UKIP
    1.15
     Ukip
    1.14
     Duterte
    1.14
     Netanyahu
    1.12
     Houth
    1.12
     Erdogan
    1.09
     Hamas
    1.08
     Rohingya
    1.06
     Rouhani
    1.05
    Activations Density 1.214%

    No Known Activations