INDEX

Explanations

phrases related to a specific person named Elizabeth Warren

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Elizabeth."

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

ursed

-0.86

acca

-0.75

yright

-0.73

²¾

-0.72

unal

-0.71

alien

-0.69

awaru

-0.68

ãĥ£

-0.67

ebin

-0.66

haps

-0.66

POSITIVE LOGITS

 Elizabeth

1.17

 Warren

1.10

Elizabeth

0.96

 Howell

0.95

 Jennings

0.90

Liu

0.84

 Holmes

0.83

 Hath

0.82

 Dodd

0.80

tis

0.80

Activations Density 0.004%

phrases related to a specific person named Elizabeth Warren

occurrences of the name "Elizabeth."

No Comments

No Known Activations