INDEX

Explanations

references to the concept of "all" in various contexts

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

all followed by noun

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

-0.31

-0.30

 Pand

-0.29

sr

-0.28

↵

-0.27

download

-0.26

".

-0.26

#:

-0.26

POSITIVE LOGITS

majánló

0.85

 ddelwed

0.83

ésultats

0.82

iſen

0.82

ðsíða

0.82

 Paglinawan

0.82

évaluateur

0.81

ſchaft

0.81

ementara

0.81

síða

0.81

Activations Density 0.034%

references to the concept of "all" in various contexts

all followed by noun

No Comments

No Known Activations