INDEX

Explanations

conversations about personal experiences and opinions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

after expressions of uncertainty

np_acts-logits-general · gemini-2.0-flash

past experience

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

="@+

-0.69

OrNil

-0.66

 defaultstate

-0.64

__*/

-0.63

">//

-0.62

interopRequire

-0.61

GOTREF

-0.60

lankton

-0.59

 anymore

-0.58

 StatefulWidget

-0.58

POSITIVE LOGITS

 pernah

1.38

เคย

1.11

有过

0.98

做过

0.91

过

0.88

曾經

0.86

曾

0.86

见过

0.85

 từng

0.85

说过

0.83

Activations Density 0.451%

conversations about personal experiences and opinions

after expressions of uncertainty

past experience

No Comments

No Known Activations