INDEX

Explanations

references to the brand "Starbucks"

oai_token-act-pair · gpt-3.5-turbo

mentions of the brand Starbucks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ysis

-0.70

uclear

-0.69

ologically

-0.68

usting

-0.65

avid

-0.65

yss

-0.65

otyp

-0.65

 conting

-0.64

onsense

-0.64

othy

-0.64

POSITIVE LOGITS

bucks

0.97

 Stores

0.87

 Coffee

0.85

 Â®

0.84

 Restaur

0.83

Store

0.82

caf

0.82

 cafes

0.80

 cafe

0.80

 Starbucks

0.79

Activations Density 0.010%

references to the brand "Starbucks"

mentions of the brand Starbucks

No Comments

No Known Activations