INDEX

Explanations

words containing the letters "es", with a focus on words where "es" appears as a standalone syllable

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

OSH

-0.65

isconsin

-0.62

glers

-0.60

 lifetime

-0.60

 extrem

-0.60

FTWARE

-0.60

è»

-0.59

sonian

-0.59

OGR

-0.59

ONSORED

-0.58

POSITIVE LOGITS

ktop

1.46

terday

1.33

liga

1.19

earchers

1.08

pec

1.06

earch

1.05

andro

1.02

eeks

0.99

ign

0.98

eed

0.97

Activations Density 0.038%

words containing the letters "es", with a focus on words where "es" appears as a standalone syllable

No Comments

No Known Activations