INDEX

Explanations

second-person pronouns and verbs related to giving approval or choices

oai_token-act-pair · gpt-3.5-turbo

references to the word "you" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 srfAttach

-0.70

ãĥ³ãĤ¸

-0.70

 Dimension

-0.69

 Flavoring

-0.68

Kat

-0.67

 Travels

-0.67

former

-0.66

lead

-0.65

 Chap

-0.65

Contents

-0.64

POSITIVE LOGITS

're

1.44

've

1.19

 guys

1.13

'll

1.06

 guessed

0.96

'd

0.96

tub

0.88

 want

0.88

 know

0.88

 wish

0.87

Activations Density 0.276%

second-person pronouns and verbs related to giving approval or choices

references to the word "you" in various contexts

No Comments

No Known Activations