INDEX

Explanations

instances of the word "started," indicating a focus on the initiation or beginning of actions or events

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

}\]

-0.85

 Coliseum

-0.82

 Gifts

-0.76

Piz

-0.75

Errorf

-0.75

 Cowper

-0.74

 Professions

-0.73

 itemprop

-0.73

KommentareTeilen

-0.73

enumi

-0.72

POSITIVE LOGITS

 started

2.43

started

2.08

 Started

2.06

 start

1.95

 STARTED

1.93

 starts

1.93

Started

1.91

STARTED

1.74

 Starts

1.73

 starting

1.71

Activations Density 0.066%

instances of the word "started," indicating a focus on the initiation or beginning of actions or events

No Comments

No Known Activations