INDEX

Explanations

occurrences of the word "have" followed by another word

oai_token-act-pair · gpt-3.5-turbo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

benefit

-0.74

icking

-0.72

Interested

-0.70

matter

-0.69

—-

-0.66

rift

-0.65

reality

-0.65

die

-0.64

eem

-0.64

iling

-0.64

POSITIVE LOGITS

 experimented

1.15

 been

1.09

 opted

1.05

 resorted

1.04

 gotten

1.02

 begun

1.02

 mastered

1.00

 chosen

0.96

 undergone

0.94

 devised

0.94

Activations Density 0.268%

occurrences of the word "have" followed by another word

No Comments

No Known Activations