INDEX

Explanations

conditional phrases indicating potential consequences or alternative outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

tanleria

-0.74

Vidite

-0.66

 &___

-0.66

 "..\..\

-0.64

 noqa

-0.63

曖昧さ回避

-0.63

 "..\..\..\

-0.62

verwijspagina

-0.61

 Italijanski

-0.59

SerializedSize

-0.59

POSITIVE LOGITS

 otherwise

0.90

 Otherwise

0.84

Otherwise

0.83

otherwise

0.83

 else

0.78

 altrimenti

0.77

 OTHERWISE

0.72

不然

0.71

否则

0.69

else

0.68

Activations Density 0.241%

conditional phrases indicating potential consequences or alternative outcomes

No Comments

No Known Activations