INDEX

Explanations

references to "keys" and "key points" in various contexts

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

The token "key" or related terms

np_acts-logits-general · gemini-2.0-flash

key occurrences and their common associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

GraphicsUnit

-0.92

expandindo

-0.80

 Viitattu

-0.72

 مصرى

-0.71

Autoritní

-0.71

nasium

-0.69

 linkovi

-0.69

ContentAsync

-0.69

IVEREF

-0.68

 pinulongan

-0.67

POSITIVE LOGITS

 keys

1.08

 Keys

0.99

keys

0.98

key

0.98

Key

0.92

hole

0.89

KEY

0.88

key

0.87

 KEYS

0.83

Keys

0.80

Activations Density 0.070%

references to "keys" and "key points" in various contexts

The token "key" or related terms

key occurrences and their common associations

No Comments

No Known Activations