INDEX

Explanations

phrases indicating hesitation, uncertainty or negative outcomes

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or lack of confidence

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 orally

-0.61

 identification

-0.56

 dissemination

-0.55

ortment

-0.53

 identities

-0.51

leigh

-0.51

 Presence

-0.50

 identity

-0.50

 EVENTS

-0.50

Origin

-0.49

POSITIVE LOGITS

 excuses

0.70

 doubt

0.69

 fault

0.68

 shortage

0.68

croft

0.66

 damned

0.65

 underestimate

0.64

essim

0.63

enario

0.63

bably

0.62

Activations Density 0.422%

phrases indicating hesitation, uncertainty or negative outcomes

phrases indicating uncertainty or lack of confidence

No Comments

No Known Activations