INDEX

Explanations

abstract negativity using words like "garbage" or "tangled", and location relationships using "in", "to", and "between"

oai_token-act-pair · gemini-2.0-flash

words related to removal or nullification

np_token-act-pair-logits · gpt-4o-mini

in/to

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

expandindo

-0.73

évaluateur

-0.66

latego

-0.65

قایناق‌لار

-0.64

AddTagHelper

-0.63

abestanden

-0.62

 Мексичка

-0.61

makeConstraints

-0.60

发表于

-0.58

 snippetHide

-0.58

POSITIVE LOGITS

 nulla

0.48

SBATCH

0.46

Off

0.46

off

0.45

Off

0.44

cela

0.43

freude

0.42

phem

0.42

zzata

0.41

オフ

0.41

Activations Density 1.956%

abstract negativity using words like "garbage" or "tangled", and location relationships using "in", "to", and "between"

words related to removal or nullification

in/to

No Known Activations