INDEX

Explanations

phrases indicating a requirement or directive for a group of people

oai_token-act-pair · gpt-3.5-turbo

references to groups or categories of individuals and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

edia

-0.76

itta

-0.68

tch

-0.64

instein

-0.63

ahime

-0.63

agger

-0.62

odcast

-0.61

epad

-0.60

 Braun

-0.59

 proverb

-0.59

POSITIVE LOGITS

 except

1.54

except

1.15

 imaginable

1.08

 whatsoever

1.06

soever

1.04

 alike

1.01

 irrespective

0.95

 facets

0.85

 regardless

0.83

 sexes

0.80

Activations Density 0.258%

phrases indicating a requirement or directive for a group of people

references to groups or categories of individuals and entities

No Comments

No Known Activations