INDEX

Explanations

instances where the document discusses making a difference or an impact

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significance or impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 diligently

-0.67

ħĭ

-0.62

IDS

-0.57

lass

-0.57

 manually

-0.56

 mathemat

-0.56

 Strategies

-0.55

gat

-0.54

razen

-0.53

 battled

-0.52

POSITIVE LOGITS

 sense

0.81

sense

0.76

 difference

0.75

 wearer

0.72

 Difference

0.71

 mockery

0.68

 impression

0.67

jar

0.67

 noticeable

0.66

 shudder

0.65

Activations Density 0.188%

instances where the document discusses making a difference or an impact

phrases indicating significance or impact

No Comments

No Known Activations