INDEX

Explanations

words related to intensity or strong emotions

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of being "indignant" or expressing indignation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ĥİ

-0.88

veyard

-0.87

sonian

-0.80

calling

-0.73

å§«

-0.71

 litter

-0.70

TION

-0.68

reens

-0.66

MQ

-0.66

zzo

-0.66

POSITIVE LOGITS

etermin

1.13

ented

1.12

ivid

1.03

irection

0.99

irect

0.97

oled

0.97

ents

0.97

icates

0.92

ependence

0.92

rawn

0.89

Activations Density 0.010%

words related to intensity or strong emotions

words related to the concept of being "indignant" or expressing indignation

No Comments

No Known Activations