INDEX

Explanations

terms related to inner and outer structures or dimensions

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

"inner" or "outer"

np_acts-logits-general · gemini-2.0-flash

inner and outer contrasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

出版年

-0.78

romyalgia

-0.62

parsedMessage

-0.61

protoimpl

-0.60

 Wiktionnaire

-0.60

canestro

-0.58

 utafitiHapana

-0.58

TintMode

-0.57

thâu

-0.57

︎

-0.56

POSITIVE LOGITS

most

0.80

MOST

0.76

 layer

0.71

 OUTER

0.69

 Inner

0.69

 INNER

0.68

 inner

0.68

 Outer

0.65

INNER

0.64

 outer

0.63

Activations Density 0.089%

terms related to inner and outer structures or dimensions

"inner" or "outer"

inner and outer contrasts

No Comments

No Known Activations