INDEX

Explanations

phrases indicating something is unique or specific

oai_token-act-pair · gpt-3.5-turbo

phrases indicating specificity and uniqueness in relation to various contexts

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

 largeDownload

-0.76

rio

-0.75

DragonMagazine

-0.73

sterdam

-0.70

rolled

-0.70

hur

-0.68

Written

-0.67

pard

-0.66

 pairs

-0.65

ivated

-0.65

POSITIVE LOGITS

ggles

0.93

pper

0.73

 perfection

0.71

cffff

0.69

 attain

0.69

 Virtue

0.68

 shore

0.68

 withstand

0.67

 behold

0.66

ppers

0.66

Activations Density 0.166%

phrases indicating something is unique or specific

phrases indicating specificity and uniqueness in relation to various contexts

No Comments

No Known Activations