INDEX

Explanations

phrases related to situational contexts or conditions

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

"in" followed by a noun

np_acts-logits-general · gemini-2.0-flash

common "in" phrases

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 quiser

-0.49

picks

-0.46

scriptcase

-0.45

robial

-0.45

 occupé

-0.44

ритори

-0.43

 possam

-0.42

 getRule

-0.42

क्षण

-0.42

したもの

-0.41

POSITIVE LOGITS

AddTagHelper

0.84

Portale

0.70

 betweenstory

0.70

 صوتيه

0.65

]]

0.64

CppCodeGen

0.64

httphttps

0.60

تقاوى

0.60

 BoxFit

0.59

 typelib

0.59

Activations Density 0.190%

phrases related to situational contexts or conditions

"in" followed by a noun

common "in" phrases

No Comments

No Known Activations