INDEX

Explanations

occurrences of the word "tin" and its variations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

"}")

-1.02

es

-0.94

ių

-0.85

Дереккөздер

-0.82

esity

-0.82

Demografia

-0.81

CreateMap

-0.80

bridization

-0.80

 Samuels

-0.79

kull

-0.79

POSITIVE LOGITS

Tin

1.73

Tin

1.70

tin

1.56

TIN

1.45

TIN

1.24

tin

1.20

 tins

1.12

 Tina

0.94

 Tind

0.93

 tinnitus

0.84

Activations Density 0.016%

occurrences of the word "tin" and its variations in the text

No Comments

No Known Activations