INDEX

Explanations

proper nouns or specific terms

oai_token-act-pair · gpt-3.5-turbo

references to significant events or objects, particularly in news or storytelling contexts

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

iencies

-0.77

 respectively

-0.72

ertain

-0.65

ctors

-0.62

 comply

-0.61

 evenly

-0.60

enegger

-0.60

ptions

-0.60

iott

-0.59

aintain

-0.59

POSITIVE LOGITS

 Called

0.73

 Something

0.71

 namely

0.70

calling

0.67

%:

0.67

Someone

0.67

HK

0.65

URA

0.64

possibly

0.64

çī

0.63

Activations Density 1.081%

proper nouns or specific terms

references to significant events or objects, particularly in news or storytelling contexts

No Comments

No Known Activations