INDEX

Explanations

instances of the word "Good" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

itets

-0.63

martre

-0.63

ِّف

-0.60

 Vogt

-0.60

BnF

-0.58

withOpacity

-0.58

webElementGuid

-0.57

Décès

-0.57

 Parkes

-0.57

 Rifles

-0.56

POSITIVE LOGITS

 good

1.67

 Good

1.62

Good

1.58

good

1.52

 GOOD

1.31

GOOD

1.23

 buena

1.06

 gute

0.94

 buona

0.82

 bonne

0.81

Activations Density 0.157%

instances of the word "Good" in various contexts

No Comments

No Known Activations