INDEX

Explanations

highly polarized positive and negative opinions expressed in natural language

oai_token-act-pair · gemini-2.0-flash

say

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

mogorov

-0.42

exitRule

-0.41

Instrucciones

-0.41

wapV

-0.41

ValueGeneration

-0.41

ГЛА

-0.40

جة

-0.40

命的

-0.40

Mutagenicity

-0.39

RegressionTest

-0.39

POSITIVE LOGITS

say

0.94

say

0.85

Say

0.83

Say

0.81

 says

0.77

 what

0.74

 Said

0.73

 SAID

0.70

SAY

0.70

 said

0.70

Activations Density 0.650%

highly polarized positive and negative opinions expressed in natural language

say

No Comments

No Known Activations