INDEX

Explanations

phrases indicating certainty or emphasis

oai_token-act-pair · gpt-3.5-turbo

hedging and uncertain adverbs that indicate degrees of likelihood or vagueness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ASE

-0.64

 Azerbai

-0.62

omorphic

-0.60

channelAvailability

-0.59

 adamant

-0.59

 tweeting

-0.57

 Gothic

-0.57

 gazing

-0.56

senal

-0.56

 donating

-0.55

POSITIVE LOGITS

 reflects

1.37

 corresponds

1.35

 coincides

1.35

 occurs

1.35

 belongs

1.35

 revolves

1.34

 involves

1.33

 proves

1.32

 translates

1.30

 represents

1.30

Activations Density 0.200%

phrases indicating certainty or emphasis

hedging and uncertain adverbs that indicate degrees of likelihood or vagueness

No Comments

No Known Activations