INDEX

Explanations

words related to geopolitics or international relations

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "bo" in various contexts

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

orial

-0.84

UAL

-0.80

ä»£

-0.71

Interstitial

-0.70

tracks

-0.66

earchers

-0.66

OPE

-0.65

pite

-0.65

 fielder

-0.64

istant

-0.63

POSITIVE LOGITS

olean

1.51

gey

1.08

oru

1.01

leans

0.97

vernment

0.96

ogle

0.94

 Bagg

0.92

xon

0.90

hari

0.89

jo

0.89

Activations Density 0.013%

words related to geopolitics or international relations

the presence of the word "bo" in various contexts

No Comments

No Known Activations