INDEX

Explanations

words related to locations, with particular focus on the city of 'Cuthbert'

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and places

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Juno

-0.67

sow

-0.62

gal

-0.62

 impulse

-0.61

schild

-0.59

recomm

-0.59

XM

-0.58

 Hath

-0.58

Â¯

-0.57

tip

-0.53

POSITIVE LOGITS

ulhu

1.19

pillar

1.03

emporary

0.92

berus

0.85

igham

0.82

estine

0.81

etary

0.80

ulative

0.80

ortium

0.79

cled

0.78

Activations Density 0.124%

words related to locations, with particular focus on the city of 'Cuthbert'

proper nouns, specifically names and places

No Comments

No Known Activations