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. 11611
    Prev
    Next
    INDEX
    Explanations

    money-related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "of the"

    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
     Donation
    -0.75
    heses
    -0.64
     rematch
    -0.62
     allot
    -0.61
    verages
    -0.60
     smell
    -0.60
     Presence
    -0.60
     grooming
    -0.59
    usp
    -0.59
    ade
    -0.58
    POSITIVE LOGITS
    ãĥ´
    0.69
    pees
    0.68
    ãĥĩãĤ£
    0.67
    å°
    0.66
     constituencies
    0.65
     whom
    0.65
    stad
    0.62
     unanswered
    0.62
    ugu
    0.62
    æŃ
    0.61
    Activations Density 0.099%

    No Known Activations