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. 16143
    Prev
    Next
    INDEX
    Explanations

    phrases related to opting in or out of subscriptions or services

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the concept of time or temporal conditions

    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
    avorite
    -0.92
    irt
    -0.70
    arte
    -0.67
    alach
    -0.67
    irts
    -0.66
    riad
    -0.65
    inav
    -0.65
    ussed
    -0.65
    ging
    -0.64
    uador
    -0.63
    POSITIVE LOGITS
    frames
    1.05
     periods
    0.80
     gestation
    0.79
     intervals
    0.78
     cycle
    0.77
    frame
    0.76
     horizon
    0.75
    zone
    0.74
     glance
    0.74
    cale
    0.71
    Activations Density 0.048%

    No Known Activations