INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

patterns or phrases involving brand names and proper nouns

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

CLS

-0.69

Prim

-0.67

past

-0.65

spec

-0.61

dust

-0.60

âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ

-0.60

Spot

-0.60

erial

-0.59

ALT

-0.58

window

-0.57

POSITIVE LOGITS

enegger

0.85

's

0.78

 himself

0.78

oglu

0.78

ledged

0.76

oulos

0.76

 herself

0.76

tsy

0.73

hedon

0.72

 Productions

0.71

Activations Density 0.231%

proper nouns or names

patterns or phrases involving brand names and proper nouns

No Comments

No Known Activations