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. 23547
    Prev
    Next
    INDEX
    Explanations

    words related to being inspired, motivated, or enthusiastic

    oai_token-act-pair · gpt-3.5-turbo

    words related to inspiration and emotional struggle

    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
    forth
    -0.76
     Split
    -0.70
    numbered
    -0.67
     ç¥ŀ
    -0.65
    matched
    -0.63
     Scotia
    -0.60
    riad
    -0.59
     Blessed
    -0.59
    elf
    -0.59
     Cosmos
    -0.59
    POSITIVE LOGITS
    atory
    1.25
    acies
    1.19
    acist
    1.12
    acles
    1.11
    ational
    1.06
    acular
    1.05
    ators
    1.05
    atorial
    1.02
    ysc
    1.01
    imental
    1.00
    Activations Density 0.017%

    No Known Activations