INDEX

Explanations

instances of high emotional intensity expressed as an adverb emphasizing the speaker's feelings

oai_token-act-pair · gpt-3.5-turbo

intensifiers or adverbs that indicate strong emotions or states of being

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

 occurs

-0.76

 originate

-0.71

ulence

-0.70

glers

-0.69

 undermines

-0.68

 lasts

-0.68

 arises

-0.68

 derives

-0.67

 translates

-0.67

 predicate

-0.66

POSITIVE LOGITS

 aware

1.17

 thankful

1.14

 glad

1.12

 proud

1.09

 fortunate

1.06

 lucky

1.05

 happy

1.01

 grateful

1.01

 afraid

1.00

 wondering

0.98

Activations Density 0.297%

instances of high emotional intensity expressed as an adverb emphasizing the speaker's feelings

intensifiers or adverbs that indicate strong emotions or states of being

No Comments

No Known Activations