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. 18381
    Prev
    Next
    INDEX
    Explanations

    phrases indicating simultaneity or concurrent actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of time

    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
     fingert
    -0.66
     stun
    -0.66
     unequ
    -0.62
     Kau
    -0.61
     basement
    -0.60
    elin
    -0.60
    avorite
    -0.60
     Fit
    -0.60
     LCS
    -0.59
     boun
    -0.59
    POSITIVE LOGITS
    女
    0.94
    frames
    0.79
    âĶĢâĶĢ
    0.79
    BUS
    0.78
    yang
    0.77
    HCR
    0.76
    days
    0.72
    essage
    0.71
    ²¾
    0.69
    cross
    0.69
    Activations Density 0.017%

    No Known Activations