INDEX

Explanations

phrases indicating a cause-and-effect relationship

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

 Archibald

-0.62

 nasel

-0.61

 suffice

-0.59

 abzu

-0.58

 intStringLen

-0.58

jadinya

-0.58

 OKAY

-0.55

 Rado

-0.54

Incompatible

-0.54

uszki

-0.54

POSITIVE LOGITS

 turn

1.47

Turn

1.18

 Turn

1.18

turn

1.10

 TURN

0.85

TURN

0.76

WaitGroup

0.69

SequentialGroup

0.69

 turno

0.68

prepareStatement

0.61

Activations Density 0.057%

phrases indicating a cause-and-effect relationship

No Comments

No Known Activations