INDEX

Explanations

references to significant or notable entities, particularly those associated with the term "Great."

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

Texts containing the word "great"

np_acts-logits-general · gemini-2.0-flash

Great followed by other words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

%)$

-0.57

 queſta

-0.55

 nakalista

-0.54

ſelf

-0.50

 Tissues

-0.49

mädchen

-0.48

AnchorStyles

-0.48

AccessorTable

-0.47

AddTagHelper

-0.46

bufio

-0.46

POSITIVE LOGITS

great

0.81

Great

0.74

GREAT

0.71

 great

0.71

 Great

0.71

 GREAT

0.65

TheGreat

0.50

WebVitals

0.43

 hebat

0.42

Tikang

0.41

Activations Density 0.063%

references to significant or notable entities, particularly those associated with the term "Great."

Texts containing the word "great"

Great followed by other words

No Comments

No Known Activations