INDEX

Explanations

prepositions and words that indicate relationships and contexts in text

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

relation and context words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

aarrggbb

-0.57

########.

-0.45

PullParser

-0.44

ToBounds

-0.42

makeText

-0.41

InputLabel

-0.40

AnimationsModule

-0.40

Panamoan

-0.40

 demás

-0.40

hôte

-0.40

POSITIVE LOGITS

 Normdatei

0.49

 Савезне

0.47

 للاسماء

0.44

 without

0.41

 فريبيس

0.40

GRANTED

0.38

 CURIAM

0.38

 úgy

0.38

__(/*!

0.38

IndentedString

0.37

Activations Density 0.117%

prepositions and words that indicate relationships and contexts in text

relation and context words

No Comments

No Known Activations