INDEX

Explanations

references to hexadecimal values and their representations

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

 للاسماء

-0.85

\{\\

-0.83

 bezeichneter

-0.82

 EconPapers

-0.80

 Процитовано

-0.73

Hozzáférés

-0.73

 صوتيه

-0.73

 esternos

-0.72

MemoryWarning

-0.72

]]=

-0.71

POSITIVE LOGITS

xff

2.92

xFF

2.15

XFF

1.21

xfe

1.14

xffff

1.10

xFFFF

1.03

xffffff

0.98

xffffffff

0.82

xFE

0.82

xFFFFFF

0.77

Activations Density 0.106%

references to hexadecimal values and their representations

No Comments

No Known Activations