INDEX

Explanations

instances of the word "to" 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 @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sauvages

-0.96

 Monfieur

-0.94

 énergé

-0.90

 pleaſure

-0.90

 scolaires

-0.89

 industriels

-0.86

 Theſe

-0.86

 againſt

-0.85

 Aplica

-0.85

 Cuen

-0.85

POSITIVE LOGITS

be

0.99

 have

0.86

 actually

0.82

can

0.76

 become

0.76

 also

0.73

 eventually

0.72

“

0.72

 appear

0.71

 could

0.70

Activations Density 0.132%

instances of the word "to" in various contexts

No Comments

No Known Activations