INDEX

Explanations

verbs indicating causality or influence

oai_token-act-pair · gpt-3.5-turbo

adverbs or phrases that indicate degree or extent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 weave

-0.64

 Feeling

-0.59

 Ethiopian

-0.58

Dip

-0.58

 pastors

-0.56

 contention

-0.55

ACL

-0.55

 Carbuncle

-0.55

ees

-0.54

 Brewery

-0.53

POSITIVE LOGITS

onto

0.78

 differently

0.74

within

0.73

BuyableInstoreAndOnline

0.72

Downloadha

0.70

eper

0.70

 srfAttach

0.70

isively

0.69

ãĤ´ãĥ³

0.68

unity

0.67

Activations Density 0.344%

verbs indicating causality or influence

adverbs or phrases that indicate degree or extent

No Comments

No Known Activations