INDEX

Explanations

expressions of uncertainty or questions regarding understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 defStyleAttr

-0.62

setContentView

-0.56

exels

-0.53

NOST

-0.53

/~

-0.52

 AttributeSet

-0.51

StoryboardSegue

-0.49

 linkovi

-0.49

utus

-0.49

stdin

-0.48

POSITIVE LOGITS

how

1.83

why

1.47

 what

1.46

 whether

1.46

how

1.12

whether

1.06

 cómo

1.01

 where

0.99

 bagaimana

0.99

why

0.98

Activations Density 0.319%

expressions of uncertainty or questions regarding understanding

No Comments

No Known Activations