INDEX

Explanations

mentions of the country "India"

oai_token-act-pair · gpt-3.5-turbo

mentions of India

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

inventoryQuantity

-0.87

tnc

-0.84

cies

-0.83

inelli

-0.83

esters

-0.80

olicy

-0.80

yright

-0.79

aukee

-0.78

RH

-0.77

escription

-0.77

POSITIVE LOGITS

ru

0.89

apolis

0.89

 Sharma

0.85

Pv

0.79

 Airlines

0.77

Rao

0.77

 Pradesh

0.74

India

0.73

ANS

0.73

 Cricket

0.73

Activations Density 0.031%

mentions of the country "India"

mentions of India

No Comments

No Known Activations