INDEX

Explanations

phrases related to processes and reactions, particularly in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

pierw

-0.52

 пожа

-0.51

phazard

-0.51

 kwanza

-0.49

 caufe

-0.49

OLF

-0.49

 theils

-0.48

Exposed

-0.48

ๆ

-0.48

 חיצוניים

-0.48

POSITIVE LOGITS

 more

0.71

AddTagHelper

0.65

PreferredItem

0.61

 very

0.58

më

0.58

مزید

0.56

*)((

0.56

 maniera

0.56

 sufficiently

0.55

)]:

0.55

Activations Density 0.621%

phrases related to processes and reactions, particularly in scientific contexts

No Comments

No Known Activations