INDEX

Explanations

phrases related to financial figures and projections

oai_token-act-pair · gpt-3.5-turbo

phrases indicating numerical figures or statistics related to timeframes

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

illary

-0.90

uum

-0.66

****************

-0.65

MSN

-0.63

UE

-0.62

KE

-0.61

STAR

-0.61

uary

-0.60

ofi

-0.59

Journal

-0.59

POSITIVE LOGITS

hang

1.09

loading

1.07

drive

1.01

priced

1.00

lord

1.00

whelming

0.99

payment

0.99

haul

0.96

clock

0.96

valued

0.92

Activations Density 0.090%

phrases related to financial figures and projections

phrases indicating numerical figures or statistics related to timeframes

No Comments

No Known Activations