INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a sense of anticipation or expectation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

xual

-0.82

 quir

-0.79

 urges

-0.77

 urge

-0.77

 coral

-0.76

 presumptive

-0.75

 ability

-0.75

 concess

-0.74

 potentially

-0.73

 regulatory

-0.73

POSITIVE LOGITS

Eventually

1.79

Then

1.72

Later

1.71

Shortly

1.63

Years

1.63

Soon

1.60

After

1.60

During

1.57

Suddenly

1.56

Upon

1.56

Activations Density 0.556%

proper nouns

phrases that indicate a sense of anticipation or expectation

No Comments

No Known Activations