INDEX

Explanations

phrases indicating expectations or predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ArrowToggle

-0.62

WAUKEE

-0.60

 BoxDecoration

-0.58

HttpClientModule

-0.57

 Hände

-0.57

janja

-0.53

 MainAxisSize

-0.53

arischen

-0.53

GenerationType

-0.52

 GoogleFonts

-0.52

POSITIVE LOGITS

 expect

4.18

 Expect

3.86

expect

3.68

Expect

3.55

 EXPECT

3.41

 expecting

3.40

 expects

3.39

 expectation

3.10

 expected

2.93

 expectations

2.83

Activations Density 0.061%

phrases indicating expectations or predictions

No Comments

No Known Activations

phrases indicating expectations or predictions

No Comments

No Known Activations