INDEX

Explanations

proper nouns related to geographical locations or organizations

oai_token-act-pair · gpt-3.5-turbo

geographic references and place names

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

iasco

-0.77

cellent

-0.70

ocument

-0.66

ongyang

-0.65

isoft

-0.64

MSN

-0.64

 Copy

-0.63

initialized

-0.62

thood

-0.60

 Instruction

-0.60

POSITIVE LOGITS

west

0.73

landers

0.67

iever

0.66

roth

0.66

east

0.66

ukong

0.65

dden

0.65

Ö

0.63

 neighbour

0.63

 ridge

0.63

Activations Density 0.119%

proper nouns related to geographical locations or organizations

geographic references and place names

No Comments

No Known Activations