INDEX

Explanations

concepts related to improvements or enhancements

oai_token-act-pair · gpt-3.5-turbo

mentions of improvements or advancements in various contexts

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

ãĥĥãĥī

-0.73

zh

-0.68

zer

-0.66

azine

-0.64

thur

-0.64

mberg

-0.62

cium

-0.62

zona

-0.62

chi

-0.61

ãĥ£

-0.61

POSITIVE LOGITS

 improvement

0.78

xual

0.77

ments

0.75

ment

0.74

Score

0.70

iants

0.68

 attainment

0.67

 agre

0.66

undown

0.66

>>\

0.65

Activations Density 0.032%

concepts related to improvements or enhancements

mentions of improvements or advancements in various contexts

No Comments

No Known Activations