INDEX

Explanations

pronouns 'we', 'it', 'you' at the beginning of sentences

oai_token-act-pair · gpt-3.5-turbo

repeatedly used pronouns, particularly "we" and "it"

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

emption

-0.80

indal

-0.77

acher

-0.74

arat

-0.73

berra

-0.72

wake

-0.69

Exit

-0.63

inter

-0.62

venient

-0.61

abo

-0.61

POSITIVE LOGITS

'll

0.86

'd

0.74

lur

0.69

 learned

0.68

've

0.67

 hereby

0.65

 scanned

0.65

 neglected

0.63

 guessed

0.62

 reverted

0.62

Activations Density 0.315%

pronouns 'we', 'it', 'you' at the beginning of sentences

repeatedly used pronouns, particularly "we" and "it"

No Comments

No Known Activations