Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5843
    Prev
    Next
    INDEX
    Explanations

    verbs related to updating and monitoring

    oai_token-act-pair · gpt-3.5-turbo

    potential updates and monitoring activities related to information sharing

    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
     guiActiveUnfocused
    -0.75
     guiName
    -0.64
    Downloadha
    -0.64
    quartered
    -0.62
    Connector
    -0.62
    hene
    -0.61
     allegedly
    -0.61
     Hebdo
    -0.60
     gripped
    -0.60
     supposedly
    -0.59
    POSITIVE LOGITS
     myself
    0.98
     gladly
    0.79
     tomorrow
    0.72
    eday
    0.69
    govtrack
    0.68
    dule
    0.68
     laun
    0.68
     ourselves
    0.68
    :]
    0.67
    adan
    0.67
    Activations Density 0.367%

    No Known Activations