INDEX

Explanations

phrases related to specific entities or brands

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific references related to popular culture

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

 urgency

-0.64

 scient

-0.61

 fortun

-0.59

 horm

-0.59

 punitive

-0.57

 sustained

-0.54

 preventive

-0.54

 overload

-0.53

 prescribed

-0.53

 assessing

-0.53

POSITIVE LOGITS

Jr

0.85

psons

0.75

Legend

0.74

Ô

0.73

Magikarp

0.71

âĸĳ

0.70

SourceFile

0.68

Ltd

0.68

 Tycoon

0.67

@@@@

0.66

Activations Density 1.138%

phrases related to specific entities or brands

proper nouns and specific references related to popular culture

No Comments

No Known Activations