INDEX

Explanations

phrases related to searching or seeking

oai_token-act-pair · gpt-3.5-turbo

instances of the word "find" and its variations, indicating a focus on searching or seeking something

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

 horm

-0.74

icago

-0.69

puff

-0.66

 concess

-0.64

 paced

-0.63

panic

-0.63

dating

-0.62

 indign

-0.62

psey

-0.61

rons

-0.61

POSITIVE LOGITS

ById

0.86

 loopholes

0.77

omething

0.75

ãĤ¦

0.74

out

0.72

ä½¿

0.72

ibility

0.72

uments

0.72

Ô

0.70

ãĤ¼

0.69

Activations Density 0.064%

phrases related to searching or seeking

instances of the word "find" and its variations, indicating a focus on searching or seeking something

No Comments

No Known Activations