INDEX

Explanations

adjectives and descriptive words used to describe multiple situations in unique contexts

oai_token-act-pair · gemini-2.0-flash

a

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/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.4.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

 orienta

-0.50

 урна

-0.50

AndEndTag

-0.49

<bos>

-0.47

 atra

-0.47

uert

-0.45

rel

-0.42

bra

-0.41

 пера

-0.41

Место

-0.40

POSITIVE LOGITS

stdc

1.07

+#+#

0.87

 فريبيس

0.73

IsContent

0.73

ismet

0.71

 resourceCulture

0.70

PyExc

0.69

mappedBy

0.68

 FetchType

0.67

NOPQRST

0.65

Activations Density 3.445%

adjectives and descriptive words used to describe multiple situations in unique contexts

a

No Comments

No Known Activations