INDEX

Explanations

proper nouns related to locations or organizations

oai_token-act-pair · gpt-3.5-turbo

the end of the document

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

 payday

-0.75

ught

-0.67

iannopoulos

-0.67

rower

-0.65

ictions

-0.63

ounter

-0.63

terday

-0.61

 detachment

-0.61

ests

-0.60

 jury

-0.60

POSITIVE LOGITS

 Breaker

0.87

 Mode

0.82

 Noir

0.79

 Wars

0.78

 Point

0.77

 Alley

0.75

Net

0.74

Vill

0.73

Squ

0.73

Craft

0.73

Activations Density 0.316%

proper nouns related to locations or organizations

the end of the document

No Comments

No Known Activations