INDEX

Explanations

instances of the word "stop" in various forms and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

hydrates

-0.91

 AssemblyCompany

-0.77

}`)

-0.74

KommentareTeilen

-0.73

données

-0.73

 ")");

-0.72

 Huxley

-0.71

mtext

-0.68

Charsets

-0.66

URLException

-0.65

POSITIVE LOGITS

 stop

2.47

 Stop

2.43

 stops

2.41

 STOP

2.37

Stop

2.31

 Stops

2.30

stop

2.29

STOP

2.19

stops

2.17

 stopped

2.06

Activations Density 0.046%

instances of the word "stop" in various forms and contexts

No Comments

No Known Activations