INDEX

Explanations

mentions of the brand "Motorola"

oai_token-act-pair · gpt-3.5-turbo

mentions of the brand Motorola

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ablishment

-0.82

alid

-0.80

lopp

-0.79

eking

-0.71

ombs

-0.70

eb

-0.69

rian

-0.68

razil

-0.68

mission

-0.68

aum

-0.67

POSITIVE LOGITS

 Motorola

1.01

 Moto

0.94

 Mobility

0.94

 Droid

0.78

Motor

0.73

 contrace

0.72

 Electronics

0.70

awei

0.70

puter

0.69

 phones

0.68

Activations Density 0.006%

mentions of the brand "Motorola"

mentions of the brand Motorola

No Comments

No Known Activations