INDEX

Explanations

instances where the word "approach" or related variations are mentioned in the text

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

 havoc

-0.70

ãĥ©ãĥ³

-0.65

rd

-0.64

grave

-0.63

watching

-0.63

ensen

-0.62

arus

-0.61

 notor

-0.61

rage

-0.60

mingham

-0.60

POSITIVE LOGITS

 toward

1.03

ologies

0.99

 towards

0.99

 approach

0.88

to

0.88

 thereto

0.85

 Approach

0.85

 pioneered

0.80

rait

0.77

finder

0.76

Activations Density 0.029%

instances where the word "approach" or related variations are mentioned in the text

No Comments

No Known Activations