INDEX

Explanations

the phrase "hadn't" 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

Демографія

-0.63

Externé

-0.54

HMIS

-0.52

cemic

-0.50

WebElementEntity

-0.50

 majeur

-0.49

 acrylique

-0.49

 fiscale

-0.49

braucher

-0.49

 разве

-0.49

POSITIVE LOGITS

 hadn

2.13

had

1.08

 Había

0.92

Had

0.92

 habían

0.91

 havia

0.90

tvguidetime

0.89

 había

0.87

Had

0.86

HAD

0.84

Activations Density 0.036%

the phrase "hadn't" in various contexts

No Comments

No Known Activations