INDEX

Explanations

phrases related to the company Amazon

oai_token-act-pair · gpt-3.5-turbo

mentions of the brand Amazon

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

boarding

-0.74

 sober

-0.74

 Schne

-0.72

ciation

-0.69

 USAF

-0.66

eday

-0.66

ezvous

-0.65

-----

-0.64

etting

-0.64

mov

-0.63

POSITIVE LOGITS

conn

0.81

culosis

0.79

 Echo

0.76

 Studios

0.75

 Alexa

0.75

 Kindle

0.74

Amazon

0.72

stores

0.70

 warehouses

0.70

omach

0.70

Activations Density 0.017%

phrases related to the company Amazon

mentions of the brand Amazon

No Comments

No Known Activations