© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 1230
    Prev
    Next
    INDEX
    Explanations

    terms related to growth and development in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    indicators of growth, change, and escalation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.91
    ologue
    -0.79
    yssey
    -0.76
    scene
    -0.76
    handle
    -0.74
    wark
    -0.73
     Carbuncle
    -0.72
    genre
    -0.70
    DragonMagazine
    -0.69
    rium
    -0.69
    POSITIVE LOGITS
     disruptions
    1.19
     disruption
    1.11
     losses
    1.08
     consolidation
    1.08
     reductions
    1.07
     amounts
    1.05
     delays
    1.04
     scrutiny
    1.04
     reliance
    1.04
     exploitation
    1.03
    Activations Density 0.201%

    No Known Activations