INDEX

Explanations

key adjectives describing important qualities or states

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyTitle

-0.78

ImageContext

-0.63

@[+][

-0.62

 coisa

-0.60

 mía

-0.59

oneofs

-0.59

bootstrapcdn

-0.59

 člov

-0.57

 popolari

-0.56

 pessoas

-0.55

POSITIVE LOGITS

own

0.89

 efforts

0.84

 counterparts

0.82

 ability

0.82

 selves

0.79

 contribution

0.76

 foray

0.76

selves

0.73

 abilities

0.72

 arsenal

0.72

Activations Density 0.383%

key adjectives describing important qualities or states

No Comments

No Known Activations