INDEX

Explanations

mentions of specific individuals in news articles

oai_token-act-pair · gpt-3.5-turbo

names of political figures and notable individuals, particularly in contexts involving actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĤ¦ãĤ¹

-0.76

izons

-0.74

inventoryQuantity

-0.71

?????-

-0.70

uries

-0.69

origin

-0.67

omatic

-0.66

olitics

-0.64

ãĤ¦

-0.62

Fi

-0.61

POSITIVE LOGITS

 interacting

1.43

 smiling

1.41

 hugging

1.40

 waving

1.37

 grinning

1.36

 reacting

1.35

 behaving

1.34

 laughing

1.33

 walking

1.31

 chatting

1.31

Activations Density 0.548%

mentions of specific individuals in news articles

names of political figures and notable individuals, particularly in contexts involving actions or events

No Comments

No Known Activations