INDEX

Explanations

dates expressed in numbers or other related numerical details

oai_token-act-pair · gpt-3.5-turbo

sentence-ending punctuation marks

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

 dich

-0.83

 dehuman

-0.83

 lifes

-0.76

 helper

-0.75

 invisible

-0.75

 imperson

-0.74

 unconscious

-0.73

 discarded

-0.71

 intrinsic

-0.70

 intangible

-0.70

POSITIVE LOGITS

 Tomorrow

1.04

 Hopefully

1.04

 Meanwhile

1.03

1.00

 Stay

0.99

 Already

0.95

 Depending

0.93

morrow

0.91

 Presumably

0.91

 Expect

0.90

Activations Density 0.829%

dates expressed in numbers or other related numerical details

sentence-ending punctuation marks

No Comments

No Known Activations