INDEX

Explanations

the word "wh" as a prefix, likely related to questions or interrogative phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

XmlAccessType

-0.69

MessageTagHelper

-0.67

WithIOException

-0.64

PerformLayout

-0.61

 chi̍t

-0.61

 commit

-0.60

älde

-0.59

SocketAddress

-0.59

 Meksiku

-0.59

paksa

-0.58

POSITIVE LOGITS

Whi

0.75

Wh

0.71

Whi

0.67

Wh

0.66

wh

0.59

whi

0.58

whi

0.56

intellij

0.55

WH

0.51

wh

0.49

Activations Density 0.091%

the word "wh" as a prefix, likely related to questions or interrogative phrases

No Comments

No Known Activations