INDEX

Explanations

negative phrases or words that indicate disapproval or caution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Vind

-0.61

tagext

-0.56

ViewFeatures

-0.55

 proposte

-0.54

 Varela

-0.53

rp

-0.51

 VIAF

-0.51

Accessors

-0.51

Leif

-0.50

ìm

-0.49

POSITIVE LOGITS

should

1.20

 Should

1.19

 should

1.13

 SHOULD

1.11

Should

1.10

hould

1.04

 shouldn

0.97

 shouldBe

0.97

 shouldnt

0.95

 Shouldn

0.93

Activations Density 0.082%

negative phrases or words that indicate disapproval or caution

No Comments

No Known Activations