INDEX

Explanations

phrases related to life lessons and self-improvement, often starting with "You."

oai_token-act-pair · gpt-3.5-turbo

the second-person pronoun "You" and its variations in different contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

¿½

-0.69

comments

-0.63

-0.61

 noting

-0.59

 forwarding

-0.58

 alleges

-0.58

 characterization

-0.57

 è£ıè¦ļéĨĴ

-0.57

farious

-0.57

itud

-0.56

POSITIVE LOGITS

 gotta

1.47

ain

1.26

 deserve

1.18

're

1.18

 wanna

1.10

 NEED

1.06

 belong

1.05

owe

1.04

 need

1.04

 MUST

1.02

Activations Density 0.282%

phrases related to life lessons and self-improvement, often starting with "You."

the second-person pronoun "You" and its variations in different contexts

No Comments

No Known Activations