INDEX

Explanations

words related to undesirable outcomes and/or critical analysis

oai_token-act-pair · gemini-2.0-flash

negative outcomes

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

 <<<<<<<<<<<<<<

-0.57

 textStatus

-0.54

iastes

-0.53

gste

-0.52

حيح

-0.52

țiuni

-0.52

 المكتبه

-0.52

wale

-0.51

τερα

-0.51

poe

-0.49

POSITIVE LOGITS

TypedDataSet

0.69

:✨

0.68

aarrggbb

0.68

 AssemblyProduct

0.65

MigrationBuilder

0.62

 jakie

0.61

awtextra

0.60

WarningLevel

0.59

 that

0.59

 <=",

0.59

Activations Density 3.400%

words related to undesirable outcomes and/or critical analysis

negative outcomes

No Comments

No Known Activations