INDEX

Explanations

references to user interface elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-1.27

expandindo

-1.21

IsMutable

-1.18

 itſelf

-1.17

 pleaſure

-1.15

StructEnd

-1.14

 myſelf

-1.12

 Jefus

-1.08

verwijspagina

-1.07

WriteBarrier

-1.06

POSITIVE LOGITS

UI

0.91

 logical

0.72

ui

0.67

 noise

0.66

0.65

“

0.65

“

0.64

 sound

0.63

cor

0.62

sw

0.60

Activations Density 0.288%

references to user interface elements

No Comments

No Known Activations