INDEX

Explanations

phrases predicting future events or outcomes

oai_token-act-pair · gpt-3.5-turbo

the word "will" and its various usages regarding future events or predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

amps

-0.67

JD

-0.65

HQ

-0.65

Reporting

-0.64

BuyableInstoreAndOnline

-0.60

Plan

-0.59

ENDED

-0.59

ocular

-0.59

 Diet

-0.59

 Sandwich

-0.59

POSITIVE LOGITS

 gladly

1.33

 inevitably

1.30

 doubtless

1.24

 undoubtedly

1.23

 surely

1.17

 likely

1.09

 continue

1.09

 soon

1.08

 eventually

1.08

 probably

1.03

Activations Density 0.264%

phrases predicting future events or outcomes

the word "will" and its various usages regarding future events or predictions

No Comments

No Known Activations