INDEX

Explanations

phrases indicating that something is not new or novel

oai_token-act-pair · gpt-3.5-turbo

the phrase "nothing new" or related expressions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thora

-0.74

chance

-0.73

 Winc

-0.71

 teasp

-0.67

 dise

-0.66

 Brach

-0.65

 retri

-0.63

oneliness

-0.61

ioxide

-0.59

ignt

-0.59

POSITIVE LOGITS

bie

0.89

yk

0.81

 arrivals

0.76

bies

0.76

born

0.74

 beginnings

0.73

foundland

0.72

PK

0.72

 colonialism

0.72

STER

0.71

Activations Density 0.051%

phrases indicating that something is not new or novel

the phrase "nothing new" or related expressions

No Comments

No Known Activations