INDEX

Explanations

references to specific years or time periods

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

antes

-0.70

Ã©e

-0.63

tec

-0.63

 thereof

-0.63

 thereby

-0.63

-0.62

 anymore

-0.62

 Catholicism

-0.61

 Judaism

-0.60

 someday

-0.60

POSITIVE LOGITS

 same

1.09

 simplest

1.05

 latter

1.04

 aforementioned

1.00

oret

1.00

atre

0.99

 latest

0.92

 foregoing

0.90

 largest

0.86

 aftermath

0.85

Activations Density 1.047%

references to specific years or time periods

occurrences of the word "the."

No Comments

No Known Activations