INDEX

Explanations

words related to negative emotions or qualities such as "awful," "horrible," and "terrible."

oai_token-act-pair · gpt-3.5-turbo

terms expressing negative evaluations or descriptions of experiences, conditions, or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ership

-0.87

pai

-0.86

irs

-0.82

ilus

-0.77

idable

-0.76

essor

-0.74

eters

-0.72

andr

-0.71

restricted

-0.71

olate

-0.70

POSITIVE LOGITS

 smelling

0.85

 sounding

0.83

 nightmares

0.82

 nightmare

0.80

 tasting

0.78

 horrible

0.76

 manners

0.75

 headache

0.74

 ordeal

0.74

 blow

0.73

Activations Density 0.035%

words related to negative emotions or qualities such as "awful," "horrible," and "terrible."

terms expressing negative evaluations or descriptions of experiences, conditions, or entities

No Comments

No Known Activations