INDEX

Explanations

verbs indicating a desire or intention to perform an action

oai_token-act-pair · gpt-3.5-turbo

phrases indicating suggestions or recommendations

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

pires

-0.79

ynthesis

-0.75

 contracted

-0.70

 Disability

-0.68

sis

-0.65

 manifest

-0.65

 manifests

-0.64

specified

-0.63

failed

-0.63

efined

-0.62

POSITIVE LOGITS

oola

0.76

Lago

0.73

 tasty

0.72

 juicy

0.71

intage

0.69

iter

0.69

marks

0.69

yip

0.68

 refreshing

0.67

 plenty

0.66

Activations Density 0.425%

verbs indicating a desire or intention to perform an action

phrases indicating suggestions or recommendations

No Comments

No Known Activations