INDEX

Explanations

uncertain or ambiguous statements regarding knowledge or understanding

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

Uncertainty or lack of knowledge

np_acts-logits-general · gemini-2.0-flash

uncertainty about exactness

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

 iconLine

-0.44

oubliez

-0.43

harapkan

-0.41

참고

-0.41

ernen

-0.41

indirect

-0.40

 destacado

-0.40

期刊论文

-0.40

 Wahrnehmung

-0.39

redund

-0.39

POSITIVE LOGITS

 exact

1.71

exact

1.50

 Exact

1.36

Exact

1.36

 precise

1.36

 exacte

1.31

 exactly

1.23

 genaue

1.18

 EXACT

1.16

precise

1.14

Activations Density 0.870%

uncertain or ambiguous statements regarding knowledge or understanding

Uncertainty or lack of knowledge

uncertainty about exactness

No Comments

No Known Activations