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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 24562
    Prev
    Next
    INDEX
    Explanations

    phrases related to working hard and putting effort into something

    oai_token-act-pair · gpt-3.5-turbo

    phrases focused on actions related to working hard and efforts towards achieving goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spaces
    -0.66
     Accounts
    -0.65
     Cust
    -0.63
     flashes
    -0.63
    hands
    -0.63
     curs
    -0.62
     Used
    -0.60
     Moments
    -0.60
     hairs
    -0.59
     Laksh
    -0.59
    POSITIVE LOGITS
     conserve
    1.26
     improve
    1.26
     promote
    1.26
     emulate
    1.24
     minimize
    1.23
     ensure
    1.21
     maximize
    1.18
     educate
    1.15
     mitigate
    1.13
     recreate
    1.12
    Activations Density 0.201%

    No Known Activations