INDEX

Explanations

references to the company Amazon

oai_token-act-pair · gpt-3.5-turbo

mentions of the company Amazon

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

boarding

-0.76

 sober

-0.72

 Schne

-0.70

etting

-0.67

-----

-0.67

ciation

-0.66

ezvous

-0.64

ROR

-0.64

otent

-0.64

eday

-0.63

POSITIVE LOGITS

conn

0.82

 Studios

0.81

 Echo

0.80

 Prime

0.79

 Alexa

0.78

ian

0.76

onom

0.74

Leaks

0.72

 warehouses

0.72

 Kindle

0.71

Activations Density 0.018%

references to the company Amazon

mentions of the company Amazon

No Comments

No Known Activations