INDEX

Explanations

mentions of financial transactions

oai_token-act-pair · gpt-3.5-turbo

instances of high-stakes decision-making or conflict

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

 Trafford

-0.58

Loading

-0.55

 Able

-0.47

 Lumia

-0.47

 derby

-0.46

 Canary

-0.46

Mig

-0.46

 Axel

-0.46

GHz

-0.46

Must

-0.45

POSITIVE LOGITS

etheless

0.91

NetMessage

0.57

gregation

0.55

ç¥ŀ

0.52

0.51

prison

0.50

 respectively

0.49

iannopoulos

0.48

collect

0.48

çī

0.48

Activations Density 3.084%

mentions of financial transactions

instances of high-stakes decision-making or conflict

No Comments

No Known Activations