INDEX

Explanations

phrases indicating upward movement or progression

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

Follows "out" or "up"

np_acts-logits-general · gemini-2.0-flash

direction and initiation

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

arangay

-0.51

ientras

-0.47

jsxFileName

-0.47

原始内容

-0.45

actéristi

-0.44

adaptiveStyles

-0.43

eventually

-0.43

 tartalomajánló

-0.43

braith

-0.42

 муніципалі

-0.42

POSITIVE LOGITS

躇

0.60

up

0.50

out

0.50

off

0.48

\]

0.47

yAxis

0.46

 Administrativna

0.45

 Alfaro

0.45

ölkerung

0.43

 away

0.43

Activations Density 0.279%

phrases indicating upward movement or progression

Follows "out" or "up"

direction and initiation

No Comments

No Known Activations