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. 9590
    Prev
    Next
    INDEX
    Explanations

    words related to cleaning, especially the action of scrubbing

    oai_token-act-pair · gpt-3.5-turbo

    references to activities or actions related to cleaning, writing, and emotional expression

    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
     whine
    -0.71
    terday
    -0.66
     Wonderland
    -0.66
     IST
    -0.66
     Fenrir
    -0.65
    avorite
    -0.65
     Hawaiian
    -0.65
     unexplained
    -0.64
     Enterprise
    -0.63
     Nost
    -0.63
    POSITIVE LOGITS
    bing
    1.76
    bed
    1.39
    bers
    1.38
    pled
    1.19
    ber
    1.18
    bled
    1.17
    bler
    1.15
    ri
    1.13
    ulations
    1.12
    ulously
    1.12
    Activations Density 0.051%

    No Known Activations