INDEX

Explanations

references to sequential or listed items in texts

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

 ddelweddau

-0.80

VIAF

-0.73

AddTagHelper

-0.67

 mukana

-0.66

 صوتيه

-0.66

 touristes

-0.66

afficheront

-0.65

 المعيارى

-0.65

 fumée

-0.65

 pouvoirs

-0.64

POSITIVE LOGITS

two

0.84

 three

0.79

 items

0.75

 four

0.73

⬇️

0.72

 types

0.72

 additional

0.68

 scenario

0.68

 list

0.67

six

0.65

Activations Density 0.309%

references to sequential or listed items in texts

No Comments

No Known Activations