INDEX

Explanations

references to quotes or sources marked with 'W'

oai_token-act-pair · gpt-3.5-turbo

instances of the letter "W" in uppercase

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

 unpre

-0.75

 gratification

-0.75

arial

-0.73

 apprehension

-0.67

 afore

-0.64

uate

-0.63

 sucker

-0.62

 locality

-0.62

İĭ

-0.60

 tion

-0.60

POSITIVE LOGITS

atts

1.30

restling

1.25

nesday

1.18

OW

1.15

orst

1.09

atson

1.09

anted

1.07

esley

1.06

atcher

1.06

izard

1.05

Activations Density 0.075%

references to quotes or sources marked with 'W'

instances of the letter "W" in uppercase

No Comments

No Known Activations