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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 17706
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "third" or "third place"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Third," often in reference to political, economic, or developmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reward
    -0.71
    è¦ļéĨĴ
    -0.71
    @#&
    -0.69
    NUM
    -0.69
    uated
    -0.66
    76561
    -0.66
    WAYS
    -0.64
    staking
    -0.64
    tra
    -0.64
    pher
    -0.63
    POSITIVE LOGITS
    rd
    1.02
     Third
    1.00
     baseman
    0.90
    ependent
    0.88
     Quarter
    0.80
    ortun
    0.78
     Reich
    0.78
     Amendment
    0.77
    eteenth
    0.76
     Eye
    0.75
    Activations Density 0.007%

    No Known Activations