INDEX

Explanations

legal terminologies and disclaimers related to warranties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 straws

-0.46

@"/

-0.45

 урна

-0.45

 stol

-0.45

 TextAlign

-0.44

lorum

-0.43

melidir

-0.43

myra

-0.43

uParam

-0.42

 Ordens

-0.41

POSITIVE LOGITS

 liability

0.86

 Haftung

0.74

 Liability

0.73

 AssemblyCulture

0.71

liability

0.70

Liability

0.70

StoryboardSegue

0.66

 liabilities

0.66

AddTagHelper

0.65

AndEndTag

0.65

Activations Density 0.292%

legal terminologies and disclaimers related to warranties

No Comments

No Known Activations