INDEX

Explanations

words and phrases that indicate significant size or importance

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

large size or importance

np_acts-logits-general · gemini-2.0-flash

size and magnitude

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

writeField

-0.45

ագրություններ

-0.45

matchCondition

-0.41

Erreferentziak

-0.39

ütfen

-0.37

insics

-0.37

ContentAlignment

-0.36

ByDefault

-0.35

TableAdapter

-0.35

CppMethod

-0.35

POSITIVE LOGITS

biggest

1.09

 biggest

1.04

huge

1.02

Biggest

1.01

 Biggest

0.96

 huge

0.95

Huge

0.93

 bigger

0.91

bigger

0.89

largest

0.86

Activations Density 0.313%

words and phrases that indicate significant size or importance

large size or importance

size and magnitude

No Comments

No Known Activations