INDEX

Explanations

phrases related to changes or trends over time

oai_token-act-pair · gpt-3.5-turbo

references to recent events or trends

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

0000000000000000

-0.70

çīĪ

-0.69

NPR

-0.66

trap

-0.66

£ı

-0.65

 shalt

-0.65

death

-0.64

STAR

-0.62

claimer

-0.62

istani

-0.62

POSITIVE LOGITS

 tandem

1.31

 popularity

1.17

 response

1.15

versely

1.13

 unison

1.08

 importance

1.07

 leaps

1.04

 favor

1.02

 prominence

1.01

 relation

1.01

Activations Density 0.125%

phrases related to changes or trends over time

references to recent events or trends

No Comments

No Known Activations