INDEX

Explanations

words and phrases followed by hyphens and terms related to formal studies

oai_token-act-pair · gemini-2.0-flash

say "-"

np_max-act-logits · gpt-5-mini Triggered by @chenshw0109

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

this

-1.05

for

-1.02

with

-1.00

that

-0.99

not

-0.98

from

-0.96

first

-0.96

will

-0.95

which

-0.94

what

-0.93

POSITIVE LOGITS

removeAttr

0.45

marginVertical

0.43

borderBottom

0.41

marginHorizontal

0.40

alignSelf

0.40

toggleClass

0.40

resizeMode

0.39

vstack

0.39

dropna

0.38

sstream

0.37

Activations Density 13.947%

words and phrases followed by hyphens and terms related to formal studies

say "-"

No Comments

No Known Activations