INDEX

Explanations

questions and prompts for audience engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

/**

-0.56

colgroup

-0.55

はじめに

-0.55

Bioaccumulative

-0.51

 uVar

-0.51

 ComVisible

-0.48

يتي

-0.47

ruptedException

-0.47

weer

-0.47

handelt

-0.46

POSITIVE LOGITS

 Tell

1.18

 tell

1.17

Tell

1.13

 TELL

1.02

 share

0.95

 Share

0.94

tell

0.91

 opinions

0.89

TELL

0.88

 telling

0.85

Activations Density 0.174%

questions and prompts for audience engagement

No Comments

No Known Activations