INDEX

Explanations

dates represented in a specific format

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Last" followed by a numerical value

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

ordes

-0.76

aunders

-0.73

kaya

-0.72

aband

-0.70

ounters

-0.68

olson

-0.64

RI

-0.62

/#

-0.62

ensical

-0.61

ocratic

-0.61

POSITIVE LOGITS

 Month

0.88

 month

0.84

 week

0.83

 Gleaming

0.81

 year

0.77

ebin

0.75

 Year

0.72

 Last

0.71

 night

0.71

 Updated

0.71

Activations Density 0.049%

dates represented in a specific format

instances of the word "Last" followed by a numerical value

No Comments

No Known Activations