INDEX

Explanations

phrases indicating possession or ownership

oai_token-act-pair · gpt-3.5-turbo

possessive forms related to people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Alert

-0.80

lein

-0.76

lehem

-0.73

ĳå£«

-0.73

arians

-0.71

Reviewer

-0.70

worm

-0.70

TAIN

-0.70

olkien

-0.70

ulhu

-0.69

POSITIVE LOGITS

own

1.25

 favourite

0.96

 belongings

0.94

 willingness

0.91

 favorite

0.91

 knees

0.89

 footsteps

0.88

 perspective

0.87

 gaze

0.86

 whereabouts

0.86

Activations Density 0.106%

phrases indicating possession or ownership

possessive forms related to people

No Comments

No Known Activations