INDEX

Explanations

HTML closing tags

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

HTML tags

np_acts-logits-general · gemini-2.0-flash

HTML structure or code blocks

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

 للاسماء

-0.71

 invokingState

-0.60

fjspx

-0.55

 ProtoMessage

-0.54

 ujednoznacz

-0.53

 transfieras

-0.49

!*\

-0.48

 ModelExpression

-0.47

 ब्रेकडाउन

-0.47

inSlope

-0.47

POSITIVE LOGITS

body

0.43

הערות

0.41

værende

0.39

BODY

0.38

mains

0.37

șe

0.36

bige

0.36

HTML

0.36

 kaynağından

0.36

html

0.35

Activations Density 0.188%

HTML closing tags

HTML tags

HTML structure or code blocks

No Comments

No Known Activations