INDEX

Explanations

phrases indicating understanding or comprehension

oai_token-act-pair · gpt-3.5-turbo

instances of the word "understood" to indicate comprehension or acknowledgment

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onies

-0.81

ads

-0.73

onto

-0.71

airs

-0.64

endar

-0.63

uns

-0.63

nar

-0.62

jay

-0.62

cephal

-0.61

guyen

-0.60

POSITIVE LOGITS

ĸļ

1.00

¿½

0.82

 understood

0.81

 Leilan

0.79

éĸ

0.78

($)

0.77

 Understand

0.76

 Sakuya

0.76

 understands

0.76

omatic

0.70

Activations Density 0.006%

phrases indicating understanding or comprehension

instances of the word "understood" to indicate comprehension or acknowledgment

No Comments

No Known Activations