INDEX

Explanations

quantitative measures related to the output or production rate

oai_token-act-pair · gpt-3.5-turbo

references to time intervals and measurements

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

actionDate

-0.72

tymology

-0.71

bley

-0.68

uador

-0.68

ĪĴ

-0.67

çĶ°

-0.65

redd

-0.63

forts

-0.62

WOR

-0.62

iland

-0.61

POSITIVE LOGITS

 increments

0.86

 thereafter

0.81

 basis

0.80

oline

0.76

Footnote

0.70

âĪĴ

0.68

 gestation

0.68

 average

0.67

asus

0.66

summary

0.66

Activations Density 0.041%

quantitative measures related to the output or production rate

references to time intervals and measurements

No Comments

No Known Activations