INDEX

Explanations

words related to decision-making or taking a firm stand on a particular issue

oai_token-act-pair · gpt-3.5-turbo

prepositions and connectors indicating relationships or actions

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

DragonMagazine

-0.56

andowski

-0.55

INESS

-0.55

edin

-0.54

hap

-0.54

NH

-0.53

orah

-0.53

okia

-0.49

imental

-0.49

verages

-0.49

POSITIVE LOGITS

 hers

0.59

 Camel

0.56

 Carbuncle

0.51

Ci

0.51

rium

0.50

 theirs

0.50

 ours

0.50

 adulthood

0.48

 Cain

0.47

 Scots

0.47

Activations Density 1.309%

words related to decision-making or taking a firm stand on a particular issue

prepositions and connectors indicating relationships or actions

No Comments

No Known Activations