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. 9052
    Prev
    Next
    INDEX
    Explanations

    the phrase "as a whole" used to describe a larger entity or group

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference unity or the idea of a collective group

    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
    minist
    -0.90
    CHAT
    -0.66
    rences
    -0.65
    olas
    -0.64
    yrinth
    -0.63
    ufact
    -0.62
    duino
    -0.60
    odore
    -0.59
    CU
    -0.59
    RANT
    -0.59
    POSITIVE LOGITS
    heartedly
    1.05
    hearted
    0.96
    meal
    0.76
    cule
    0.67
     organism
    0.67
    allo
    0.65
     panc
    0.64
    osaurus
    0.62
    âĶĢâĶĢâĶĢâĶĢ
    0.60
     ordeal
    0.59
    Activations Density 0.021%

    No Known Activations