INDEX

Explanations

occurrences of the word "to" and its various forms 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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 pleaſure

-1.17

 Monfieur

-1.08

 againſt

-1.04

 myſelf

-0.97

 Jefus

-0.95

 houſe

-0.94

 purpoſe

-0.91

 scolaires

-0.91

 becauſe

-0.90

 itſelf

-0.89

POSITIVE LOGITS

be

1.00

“

0.92

 become

0.79

 have

0.78

not

0.73

’

0.73

 must

0.72

‘

0.71

0.70

had

0.69

Activations Density 0.129%

occurrences of the word "to" and its various forms in the text

No Comments

No Known Activations