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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7024
    Prev
    Next
    INDEX
    Explanations

    mentions of taking time away from work to focus on personal passions and writing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal time management and prioritizing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.85
     Cosponsors
    -0.80
    Height
    -0.76
    CVE
    -0.70
    ochet
    -0.69
    士
    -0.68
    itudinal
    -0.68
    apego
    -0.67
    etheus
    -0.65
    é¾į
    -0.65
    POSITIVE LOGITS
     chores
    1.46
     hobbies
    1.30
     duties
    1.27
     tasks
    1.23
     pursuits
    1.21
     busy
    1.11
     activities
    1.11
     work
    1.02
     mundane
    1.02
     homework
    1.02
    Activations Density 0.470%

    No Known Activations