INDEX

Explanations

questions and statements that include the word "Shouldn't"

oai_token-act-pair · gpt-3.5-turbo

the word "shouldn't" and its variations, indicating questions about rights and responsibilities

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

è¦ļéĨĴ

-0.68

 laun

-0.67

 winding

-0.66

 helicop

-0.61

 ignited

-0.60

 pressured

-0.59

gap

-0.58

 flooded

-0.58

orc

-0.57

 Mour

-0.57

POSITIVE LOGITS

't

1.05

aught

0.89

ovation

0.82

auts

0.79

intend

0.75

udge

0.73

itely

0.72

odd

0.72

acular

0.72

eat

0.70

Activations Density 0.024%

questions and statements that include the word "Shouldn't"

the word "shouldn't" and its variations, indicating questions about rights and responsibilities

No Comments

No Known Activations