INDEX

Explanations

phrases related to anticipation or expectation

oai_token-act-pair · gpt-3.5-turbo

words related to anticipation or events yet to occur

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

caps

-0.68

vil

-0.66

arse

-0.65

ouf

-0.65

midt

-0.65

audi

-0.64

xa

-0.64

iane

-0.63

Cola

-0.63

blue

-0.63

POSITIVE LOGITS

 awaiting

1.05

 await

1.05

 patiently

1.05

 awaits

0.97

 awaited

0.93

 eagerly

0.85

 arrival

0.78

ilee

0.78

ITNESS

0.76

atcher

0.75

Activations Density 0.012%

phrases related to anticipation or expectation

words related to anticipation or events yet to occur

No Comments

No Known Activations