INDEX

Explanations

phrases indicating events or actions happening before and after something

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate comparisons of events or conditions occurring before and after a specific point in time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Journals

-0.61

gur

-0.60

agy

-0.60

illi

-0.60

 Petr

-0.60

WARE

-0.59

 Kard

-0.58

Fram

-0.58

ADRA

-0.58

Merit

-0.57

POSITIVE LOGITS

aft

0.97

during

0.89

behind

0.78

rogen

0.78

 during

0.77

ecycle

0.76

rogens

0.76

isode

0.73

present

0.73

 AFTER

0.71

Activations Density 0.052%

phrases indicating events or actions happening before and after something

phrases that indicate comparisons of events or conditions occurring before and after a specific point in time

No Comments

No Known Activations