INDEX

Explanations

terms related to leadership positions or titles

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Super"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

-0.85

gow

-0.76

edin

-0.68

 Twain

-0.67

assetsadobe

-0.66

 Seym

-0.65

llers

-0.64

 ........

-0.63

edIn

-0.63

 Greenwald

-0.63

POSITIVE LOGITS

visor

1.15

intendent

1.07

ior

0.98

nova

0.97

imposed

0.95

visory

0.94

IOR

0.94

visors

0.93

computer

0.90

marine

0.87

Activations Density 0.007%

terms related to leadership positions or titles

occurrences of the word "Super"

No Comments

No Known Activations