INDEX

Explanations

personal pronouns 'I' or 'I'm'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the pronoun "I" indicating personal expression or perspective

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 adhesive

-0.68

 selves

-0.64

 markings

-0.64

 electromagnetic

-0.62

 deeds

-0.62

 souls

-0.60

 ingred

-0.59

 ç¥ŀ

-0.59

 membrane

-0.59

 unfocusedRange

-0.58

POSITIVE LOGITS

'm

1.14

've

1.08

ronic

1.04

xtap

1.03

vana

1.02

nex

1.02

 suppose

1.02

'll

0.98

rina

0.98

deals

0.98

Activations Density 0.146%

personal pronouns 'I' or 'I'm'

occurrences of the pronoun "I" indicating personal expression or perspective

No Comments

No Known Activations