INDEX

Explanations

mentions of the word "Green"

oai_token-act-pair · gpt-3.5-turbo

references to the term "Green" and its associations

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

 anat

-0.87

tyr

-0.79

 seiz

-0.78

DOM

-0.76

 abdom

-0.76

 disse

-0.71

iat

-0.69

 consolid

-0.69

 sarc

-0.67

 skelet

-0.67

POSITIVE LOGITS

 Green

3.69

Green

3.02

 GREEN

2.42

 Greens

2.32

green

2.20

 green

2.13

GREEN

1.92

 Purple

1.69

 Blue

1.66

 greens

1.63

Activations Density 0.016%

mentions of the word "Green"

references to the term "Green" and its associations

No Comments

No Known Activations