INDEX

Explanations

proper nouns related to individuals or locations

oai_token-act-pair · gpt-3.5-turbo

specific names or terms related to organizations, places, or notable figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ariat

-0.72

\\

-0.67

ient

-0.65

 Murd

-0.63

Coy

-0.62

\\

-0.61

pard

-0.61

igham

-0.60

 Yard

-0.60

 Militia

-0.60

POSITIVE LOGITS

ommel

3.18

ramer

2.38

Sax

1.31

ABV

1.12

roma

1.02

 roadside

1.00

Vij

0.99

USS

0.91

 trivia

0.89

ellen

0.82

Activations Density 0.050%

proper nouns related to individuals or locations

specific names or terms related to organizations, places, or notable figures

No Comments

No Known Activations