INDEX

Explanations

phrases related to updates or announcements

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "We" and its variations, indicating a focus on collective or inclusive statements

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

forms

-0.59

 guiActiveUnfocused

-0.59

panic

-0.58

REDACTED

-0.58

 eviction

-0.58

 flows

-0.57

Reply

-0.56

 Leilan

-0.56

âĸ¬

-0.55

 Flavoring

-0.55

POSITIVE LOGITS

're

1.17

eks

1.06

athered

1.05

've

1.03

asel

1.02

igh

1.02

akening

1.00

ibo

0.99

arers

0.99

'll

0.96

Activations Density 0.138%

phrases related to updates or announcements

the presence of the word "We" and its variations, indicating a focus on collective or inclusive statements

No Comments

No Known Activations