INDEX

Explanations

phrases containing the word "our"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "our" emphasizing shared experiences or collective ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WAR

-0.70

 Rasmussen

-0.68

FU

-0.68

 Rove

-0.66

DERR

-0.63

 Crosby

-0.63

 Tanz

-0.61

 Lovecraft

-0.59

aughtered

-0.59

 buckle

-0.58

POSITIVE LOGITS

selves

1.32

neau

1.09

neys

1.06

dain

0.95

cery

0.93

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

0.89

ishment

0.89

izons

0.86

izont

0.83

idine

0.81

Activations Density 0.018%

phrases containing the word "our"

instances of the word "our" emphasizing shared experiences or collective ownership

No Comments

No Known Activations