INDEX

Explanations

words that are commonly used adjectives and adverbs

oai_token-act-pair · gemini-2.0-flash

like

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tartalomajánló

-0.74

RegressionTest

-0.67

GEBURTSDATUM

-0.65

AddTagHelper

-0.65

 intptr

-0.64

SourceChecksum

-0.63

__":

-0.62

AndPassword

-0.60

protoimpl

-0.60

 inkább

-0.58

POSITIVE LOGITS

isSuccessful

0.47

ImGui

0.47

antly

0.46

resultCode

0.45

teis

0.44

勉

0.43

 assumption

0.43

OpenHelper

0.43

leste

0.41

lote

0.41

Activations Density 19.400%

words that are commonly used adjectives and adverbs

like

No Comments

No Known Activations