INDEX

Explanations

personal pronouns followed by actions or states that hold significance

oai_token-act-pair · gpt-3.5-turbo

first-person pronouns and their references in context

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

 Globe

-0.89

 Akron

-0.79

 Aden

-0.71

 Leban

-0.70

aceutical

-0.70

 Hague

-0.69

 Kush

-0.66

 Kinn

-0.65

adan

-0.65

Yel

-0.64

POSITIVE LOGITS

'd

1.12

'll

1.11

've

1.07

're

1.04

'm

0.91

 could

0.88

 shouldn

0.86

 couldn

0.80

ould

0.78

RL

0.77

Activations Density 0.228%

personal pronouns followed by actions or states that hold significance

first-person pronouns and their references in context

No Comments

No Known Activations