INDEX

Explanations

the word "exactly" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Autoritní

-0.70

gameserver

-0.68

)="

-0.68

 invokingState

-0.66

Portale

-0.64

 pulumi

-0.62

 betweenstory

-0.62

Collegamenti

-0.60

يكب

-0.58

Guido

-0.58

POSITIVE LOGITS

 same

0.89

same

0.80

 Exactly

0.75

 Same

0.73

Same

0.72

 opposite

0.71

 exactly

0.70

 SAME

0.68

 mismos

0.67

 Opposite

0.65

Activations Density 0.098%

the word "exactly" and its variations in context

No Comments

No Known Activations