INDEX

Explanations

words related to surveillance or being surrounded

oai_token-act-pair · gpt-3.5-turbo

instances of the word "surprising" and its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 tense

-0.65

hetti

-0.64

 centralized

-0.63

 numbering

-0.63

naires

-0.62

 habitable

-0.60

 subsystem

-0.60

 amber

-0.59

 calendars

-0.59

 sender

-0.58

POSITIVE LOGITS

geon

1.49

rounded

1.36

geons

1.33

render

1.26

prising

1.26

round

1.22

prise

1.19

prises

1.18

vey

1.18

fing

1.17

Activations Density 0.025%

words related to surveillance or being surrounded

instances of the word "surprising" and its derivatives

No Comments

No Known Activations