INDEX

Explanations

specific numerical values or codes related to medical or scientific data

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

 myſelf

-1.17

Efq

-1.01

ſelf

-0.96

 ſche

-0.94

 pinulongan

-0.94

 itſelf

-0.92

 ainfi

-0.92

 Normdatei

-0.92

 ſeveral

-0.91

 ་་

-0.91

POSITIVE LOGITS

0.80

0.72

po

0.66

↵↵

0.61

0.59

0.58

по

0.58

Po

0.57

得

0.56

Activations Density 0.255%

specific numerical values or codes related to medical or scientific data

No Comments

No Known Activations