INDEX

Explanations

verbs or verb phrases related to hypothetical scenarios

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "had" and its contextual implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 intens

-0.61

 redef

-0.59

 brink

-0.58

 unveiling

-0.57

 parody

-0.56

hammer

-0.53

 Extreme

-0.53

 hilarious

-0.53

 reprint

-0.52

 pinnacle

-0.52

POSITIVE LOGITS

 been

1.26

 gotten

1.14

been

1.11

 stayed

1.01

 behaved

0.99

 intervened

0.99

 waited

0.95

gotten

0.95

 existed

0.94

 gone

0.93

Activations Density 0.142%

verbs or verb phrases related to hypothetical scenarios

instances of the verb "had" and its contextual implications

No Comments

No Known Activations