INDEX

Explanations

instances of the word "by" and its variations in the context of actions or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

dotenv

-0.47

POSURE

-0.45

jen

-0.44

Παραπομπές

-0.40

 Schult

-0.39

Mas

-0.39

adhé

-0.39

 suscripción

-0.38

POSITIVE LOGITS

Personensuche

1.11

 Roskov

0.93

HandlerContext

0.87

 betweenstory

0.85

NamedQueries

0.81

 noqa

0.79

ValueStyle

0.78

findpost

0.78

 AssemblyCulture

0.77

 itſelf

0.74

Activations Density 0.180%

instances of the word "by" and its variations in the context of actions or descriptions

No Comments

No Known Activations