INDEX

Explanations

phrases related to exclamatory statements that start with "Not"

oai_token-act-pair · gpt-3.5-turbo

the repeated negation or expressions of disagreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĥ

-0.76

è¦ļéĨĴ

-0.74

assetsadobe

-0.71

ç·

-0.71

stakes

-0.70

å¤§

-0.70

è£

-0.69

=-=-=-=-

-0.67

 Mehran

-0.67

è¡

-0.67

POSITIVE LOGITS

epad

1.23

 necessarily

1.16

withstanding

1.14

icably

1.12

orious

1.04

eworthy

1.00

ices

0.94

ifications

0.91

yet

0.89

icable

0.89

Activations Density 0.129%

phrases related to exclamatory statements that start with "Not"

the repeated negation or expressions of disagreement

No Comments

No Known Activations