INDEX

Explanations

instances of the word "explore" and its variations, indicating a focus on exploration or inquiry

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

Texts mentioning "explore" or "exploration"

np_acts-logits-general · gemini-2.0-flash

exploring and investigating

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

jsonwebtoken

-0.62

 PopupWindow

-0.61

 surla

-0.59

 censiti

-0.57

 <>",

-0.56

GOTREF

-0.55

transQ

-0.55

ValueStyle

-0.54

DotNetBar

-0.53

 חיצוניים

-0.52

POSITIVE LOGITS

 explor

0.84

 explore

0.78

 exploration

0.69

 exploring

0.68

 Explore

0.68

 explorar

0.67

 explorer

0.66

 Explor

0.66

explor

0.66

 explored

0.64

Activations Density 0.108%

instances of the word "explore" and its variations, indicating a focus on exploration or inquiry

Texts mentioning "explore" or "exploration"

exploring and investigating

No Comments

No Known Activations