INDEX

Explanations

sentences starting with "We" and possibly describing plans, actions, or intentions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "We"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Appearances

-0.69

cum

-0.67

Reviewer

-0.65

 totality

-0.60

nesota

-0.59

["

-0.59

 Bundy

-0.58

math

-0.57

netflix

-0.56

atory

-0.56

POSITIVE LOGITS

're

1.28

've

1.21

bsite

1.14

 strive

1.10

'll

1.08

akening

1.07

 recommend

1.06

 apologize

1.02

 encourage

0.99

ighed

0.99

Activations Density 0.217%

sentences starting with "We" and possibly describing plans, actions, or intentions

instances of the word "We"

No Comments

No Known Activations