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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2327
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic conditions and sanctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moreover
    -0.60
     furthermore
    -0.57
     Brilliant
    -0.55
    eday
    -0.54
    ":["
    -0.53
     Ibid
    -0.51
     therefore
    -0.51
     CrossRef
    -0.49
     analogous
    -0.49
     Cunning
    -0.49
    POSITIVE LOGITS
    quit
    0.72
     slump
    0.56
    ussions
    0.55
     misconduct
    0.51
     Belfast
    0.51
     dismissal
    0.50
    angan
    0.50
     penalties
    0.49
    ped
    0.49
     exit
    0.48
    Activations Density 1.505%

    No Known Activations