© 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. 9-RES-JB
    11. 3609
    Prev
    Next
    INDEX
    Explanations

    information related to being the first to do or know something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating being the first to know or experience something

    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
     embodiments
    -0.71
     representations
    -0.69
     fortun
    -0.66
     thous
    -0.65
    ĺħ
    -0.62
     Replacement
    -0.61
     assurance
    -0.61
     Powers
    -0.60
     altern
    -0.60
    lav
    -0.58
    POSITIVE LOGITS
     admit
    1.06
     arrive
    1.05
     congratulate
    1.03
     realize
    0.99
     realise
    0.98
    ggles
    0.93
     succumb
    0.92
     acknowledge
    0.90
     respond
    0.90
     criticize
    0.89
    Activations Density 0.062%

    No Known Activations