INDEX

Explanations

adjectives describing things as clear and direct

oai_token-act-pair · gpt-3.5-turbo

terms related to simplicity and clarity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

akin

-0.73

reen

-0.66

ingle

-0.66

wives

-0.65

 Seeds

-0.63

aughters

-0.63

aden

-0.62

psey

-0.61

olina

-0.60

 whales

-0.60

POSITIVE LOGITS

ly

1.18

 straightforward

1.02

lly

0.98

LY

0.88

tons

0.81

itably

0.81

ity

0.81

é¾

0.80

\\\\\\\\

0.80

NESS

0.78

Activations Density 0.019%

adjectives describing things as clear and direct

terms related to simplicity and clarity

No Comments

No Known Activations