INDEX

Explanations

phrases related to actions taken or decisions made by different entities or individuals

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ety

-0.67

etc

-0.66

orph

-0.64

Soc

-0.63

hack

-0.63

bery

-0.63

igious

-0.61

eth

-0.58

edy

-0.58

awa

-0.57

POSITIVE LOGITS

 hoped

1.36

iths

1.14

 originally

1.08

 planned

1.03

 previously

0.98

 initially

0.92

 begun

0.91

 been

0.89

 anticipated

0.88

 earlier

0.87

Activations Density 0.179%

phrases related to actions taken or decisions made by different entities or individuals

No Comments

No Known Activations