INDEX

Explanations

personal pronouns 'I' indicating self-referential statements

oai_token-act-pair · gpt-3.5-turbo

expressions that indicate personal experiences or opinions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ħ¢

-0.64

 Rapids

-0.62

rules

-0.61

 Reef

-0.60

 tides

-0.58

 Pearson

-0.58

 Grove

-0.57

 Shelby

-0.57

 Redmond

-0.57

 Slav

-0.57

POSITIVE LOGITS

'm

1.30

've

1.07

 suppose

1.06

 dunno

1.03

nex

1.03

zzy

1.01

'll

1.00

xtap

0.97

WI

0.96

EEE

0.96

Activations Density 0.085%

personal pronouns 'I' indicating self-referential statements

expressions that indicate personal experiences or opinions

No Comments

No Known Activations