INDEX

Explanations

instances of the word "Almost" followed by an action or description

oai_token-act-pair · gpt-3.5-turbo

the word "almost" and similar qualifiers indicating approximation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 reserve

-0.74

 specific

-0.73

 repr

-0.70

 other

-0.69

 special

-0.69

 mate

-0.66

 corresponding

-0.65

 particular

-0.64

 prior

-0.64

 right

-0.63

POSITIVE LOGITS

Almost

2.54

Nearly

2.35

 Nearly

2.13

 Almost

2.02

almost

1.77

Quite

1.30

Most

1.29

Much

1.28

Half

1.27

 Surprisingly

1.24

Activations Density 0.014%

instances of the word "Almost" followed by an action or description

the word "almost" and similar qualifiers indicating approximation

No Comments

No Known Activations