© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 22852
    Prev
    Next
    INDEX
    Explanations

    phrases related to setting and achieving goals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to achieving goals or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dayName
    -0.69
    cloth
    -0.69
    letter
    -0.64
    say
    -0.62
    osate
    -0.62
     Printed
    -0.61
    WARN
    -0.60
     Tactics
    -0.60
     Cells
    -0.59
    shop
    -0.59
    POSITIVE LOGITS
     parity
    1.12
     immortality
    0.98
     goals
    0.96
     objectives
    0.95
     greatness
    0.95
     perfection
    0.94
     unanim
    0.91
     milestones
    0.90
     notoriety
    0.89
     excellence
    0.89
    Activations Density 0.074%

    No Known Activations