INDEX

Explanations

instructions or tips beginning with "If you have."

oai_token-act-pair · gpt-3.5-turbo

phrases indicating possession or requirements related to the reader's experiences and 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

"},

-0.74

hu

-0.68

Els

-0.67

ãĥķ

-0.67

burgh

-0.65

Js

-0.64

Dub

-0.63

DragonMagazine

-0.63

NetMessage

-0.61

"},{"

-0.60

POSITIVE LOGITS

 unsure

0.76

 lucky

0.73

 inclined

0.70

 DEBUG

0.68

 unlucky

0.66

audi

0.65

 interested

0.64

ileged

0.64

 yourself

0.63

 subscrib

0.63

Activations Density 0.234%

instructions or tips beginning with "If you have."

phrases indicating possession or requirements related to the reader's experiences and actions

No Comments

No Known Activations