INDEX

Explanations

phrases indicating understanding or comprehension

oai_token-act-pair · gpt-3.5-turbo

instances of the word "understands."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

drop

-0.61

bearing

-0.61

 resulting

-0.60

 Â«

-0.59

gra

-0.59

 Boll

-0.58

 bearing

-0.58

 spring

-0.58

 dubious

-0.57

 random

-0.57

POSITIVE LOGITS

 understands

3.53

 knows

1.89

 understood

1.87

 understand

1.80

 realizes

1.77

 recognizes

1.73

 believes

1.60

 learns

1.58

 Understand

1.52

 accepts

1.51

Activations Density 0.013%

phrases indicating understanding or comprehension

instances of the word "understands."

No Comments

No Known Activations