INDEX

Explanations

phrases that indicate surprise or unexpected outcomes

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

"surprise"

np_acts-logits-general · gemini-2.0-flash

not surprising or expected

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 समीक्षाएं

-0.68

ArgsConstructor

-0.52

HtmlAttribute

-0.51

CHAFT

-0.51

 devoirs

-0.48

={({

-0.46

懸命

-0.46

 gogh

-0.46

клей

-0.45

 تانيه

-0.45

POSITIVE LOGITS

 surprise

3.27

 surprises

2.80

surprise

2.74

 surprised

2.72

 Surprise

2.67

Surprise

2.66

 surprising

2.46

 surpris

2.27

 sorpresa

2.25

 shock

2.25

Activations Density 0.278%

phrases that indicate surprise or unexpected outcomes

"surprise"

not surprising or expected

No Comments

No Known Activations