INDEX

Explanations

instances of people expressing their opinions

oai_token-act-pair · gemini-2.0-flash

feel

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

UniformLocation

-0.52

 thought

-0.50

 Thought

-0.49

ImageContext

-0.49

imab

-0.47

nteral

-0.47

eff

-0.46

lactin

-0.45

Thought

-0.44

 kern

-0.44

POSITIVE LOGITS

 betweenstory

0.70

ftagPool

0.68

سطس

0.65

 initComponents

0.63

PhysRevD

0.62

Референце

0.61

HasOne

0.57

MigrationBuilder

0.55

 ashamed

0.55

we

0.55

Activations Density 0.353%

instances of people expressing their opinions

feel

No Comments

No Known Activations