INDEX

Explanations

words related to confrontation or conflict

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'c'

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

words that start with the letter 'c'

oai_token-act-pair · gpt-4-turbo

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

é¾įå

-0.94

 GOODMAN

-0.91

å§«

-0.82

DragonMagazine

-0.81

tenance

-0.80

ãĤ¤ãĥĪ

-0.79

éĹĺ

-0.79

Magikarp

-0.76

ãĥĹ

-0.74

Ô

-0.73

POSITIVE LOGITS

rosso

1.06

ordon

1.03

uffed

1.01

ologne

0.98

oder

0.97

olly

0.96

osponsors

0.95

rescent

0.93

umb

0.91

overed

0.91

Activations Density 0.020%

words related to confrontation or conflict

occurrences of the letter 'c'

words that start with the letter 'c'

No Comments

No Known Activations