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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 21064
    Prev
    Next
    INDEX
    Explanations

    phrases related to organization and management, particularly focusing on "keeping" tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of maintaining or managing something

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

    No Comments

    Negative Logits
    NetMessage
    -0.77
    Interstitial
    -0.68
    lik
    -0.67
    OUN
    -0.66
    emphasis
    -0.64
     Bowen
    -0.63
    oute
    -0.61
    Merit
    -0.61
     VIDEOS
    -0.59
    LAN
    -0.58
    POSITIVE LOGITS
     vigil
    0.96
     tabs
    0.87
     track
    0.86
     afloat
    0.83
     pace
    0.83
    tracks
    0.82
     alive
    0.81
    keeping
    0.81
     kosher
    0.78
     intact
    0.74
    Activations Density 0.021%

    No Known Activations