INDEX

Explanations

reported speech or quotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Majefty

-0.79

ſelves

-0.77

 betweenstory

-0.75

 leſs

-0.75

AndEndTag

-0.75

 ſeveral

-0.74

 pleaſure

-0.74

 الحره

-0.73

 houſe

-0.72

 Diſ

-0.70

POSITIVE LOGITS

the

0.71

it

0.64

 there

0.57

GroupLayout

0.57

cuma

0.56

AppMethodBeat

0.52

if

0.51

“

0.50

he

0.49

Activations Density 0.154%

reported speech or quotations

No Comments

No Known Activations