INDEX

Explanations

instances where an estimated numeric value is mentioned in relation to a specific subject

oai_token-act-pair · gpt-3.5-turbo

phrases or terms indicating estimations or approximations of quantities

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

woods

-0.92

feeding

-0.81

marine

-0.78

oard

-0.77

washer

-0.76

uits

-0.71

neys

-0.71

nered

-0.70

GU

-0.70

gob

-0.70

POSITIVE LOGITS

 estimates

0.76

 seventy

0.76

 amount

0.74

è¦ļéĨĴ

0.73

imate

0.73

 estimated

0.71

 sixty

0.71

 average

0.70

 elapsed

0.70

 eighty

0.70

Activations Density 0.018%

instances where an estimated numeric value is mentioned in relation to a specific subject

phrases or terms indicating estimations or approximations of quantities

No Comments

No Known Activations