INDEX

Explanations

the use of the word "to" in various contexts

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

"To" followed by a verb

np_acts-logits-general · gemini-2.0-flash

to introduce a point

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

principalTable

-0.99

thâu

-0.85

TagMode

-0.79

principalColumn

-0.76

 otomatig

-0.76

السكان

-0.75

 <=",

-0.71

aarrggbb

-0.70

يكب

-0.68

XmlAccessType

-0.67

POSITIVE LOGITS

 summarize

0.83

 quote

0.82

 recap

0.77

 summarise

0.73

 paraphrase

0.73

 illustrate

0.72

sum

0.70

 complicate

0.70

 pior

0.64

 reiterate

0.64

Activations Density 0.090%

the use of the word "to" in various contexts

"To" followed by a verb

to introduce a point

No Comments

No Known Activations