INDEX

Explanations

adverbs expressing a level of certainty or confidence

oai_token-act-pair · gpt-3.5-turbo

phrases indicating agreement or affirmation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hend

-0.77

ourses

-0.73

endant

-0.65

endants

-0.65

ert

-0.64

¿½

-0.62

Application

-0.62

vertisement

-0.62

(\

-0.61

heid

-0.60

POSITIVE LOGITS

 kidding

0.84

literally

0.76

 boring

0.65

 REALLY

0.65

shit

0.64

 Asgard

0.63

 blah

0.62

exc

0.62

 disposable

0.62

 cursed

0.61

Activations Density 0.260%

adverbs expressing a level of certainty or confidence

phrases indicating agreement or affirmation

No Comments

No Known Activations