INDEX

Explanations

years mentioned as '2011'

oai_token-act-pair · gpt-3.5-turbo

mentions of the year 2011

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 volunte

-0.99

srf

-0.88

phy

-0.87

onite

-0.87

 cumbers

-0.85

ntil

-0.82

 satell

-0.79

 tradem

-0.77

 unin

-0.77

 councill

-0.76

POSITIVE LOGITS

å¹

1.10

-'

0.86

worthiness

0.83

ãģ®éŃĶ

0.80

0.77

 onwards

0.76

0.75

0.74

Activations Density 0.019%

years mentioned as '2011'

mentions of the year 2011

No Comments

No Known Activations