INDEX

Explanations

discussions about scientific concepts and conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

 check

-0.51

check

-0.49

 Pollut

-0.45

tagHelperRunner

-0.44

回忆

-0.43

 semilla

-0.43

 memenuhi

-0.43

checks

-0.43

 Nachfrage

-0.43

POSITIVE LOGITS

 discoveries

0.95

 scientists

0.86

scienti

0.81

 Scientists

0.79

Scientists

0.77

ModelAdmin

0.76

 biologists

0.76

OGND

0.75

didReceive

0.74

 scientist

0.73

Activations Density 0.922%

discussions about scientific concepts and conclusions

No Comments

No Known Activations