INDEX

Explanations

terms related to legal or official document verification and branding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 BoxFit

-0.64

yntaxException

-0.58

 समीक्षाओं

-0.57

volley

-0.56

 EINVAL

-0.56

 παρά

-0.54

mybatisplus

-0.54

 bào

-0.53

($__

-0.53

 onCreateView

-0.53

POSITIVE LOGITS

 mark

1.22

 marks

1.16

 marca

1.11

 logo

1.11

 trademarks

1.10

 seal

1.08

 brands

1.05

marken

1.04

 label

1.04

marks

1.03

Activations Density 0.378%

terms related to legal or official document verification and branding

No Comments

No Known Activations