INDEX

Explanations

contractions of "have" and "ve"

oai_token-act-pair · gpt-3.5-turbo

phrases that include the contraction "we've."

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

eem

-0.67

ealing

-0.63

Reviewer

-0.61

ancing

-0.60

UE

-0.60

rative

-0.60

 Torrent

-0.59

Subject

-0.59

eller

-0.58

ace

-0.57

POSITIVE LOGITS

 gotta

1.44

 been

1.37

been

1.37

got

1.22

 Been

1.18

 gotten

1.16

 undergone

0.93

 gone

0.92

hran

0.90

gotten

0.89

Activations Density 0.043%

contractions of "have" and "ve"

phrases that include the contraction "we've."

No Comments

No Known Activations