© 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. 6-RES-JB
    11. 14038
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to being the best or most important

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crown."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ABE
    -0.68
    obiles
    -0.68
     Schwar
    -0.67
    edia
    -0.66
     partName
    -0.65
    otive
    -0.65
     Dragonbound
    -0.65
     Rapp
    -0.61
     Haas
    -0.60
    ARP
    -0.60
    POSITIVE LOGITS
     jewel
    1.13
     jewels
    1.12
    pin
    1.00
    pins
    0.97
     crown
    0.96
     prince
    0.94
    ingen
    0.88
     crowned
    0.86
    ing
    0.84
    win
    0.78
    Activations Density 0.016%

    No Known Activations