INDEX

Explanations

mentions of political figures and events

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

 altogether

-0.75

intend

-0.70

*.

-0.67

ãĥĥãĥī

-0.66

—"

-0.65

 dime

-0.65

 somehow

-0.64

etheless

-0.64

encers

-0.64

POSITIVE LOGITS

 graduation

0.76

 portrait

0.73

 ceremony

0.71

 rall

0.70

 REUTERS

0.69

 entrance

0.68

 photoc

0.67

window

0.67

 Presidential

0.66

 Wikimedia

0.66

Activations Density 0.204%

mentions of political figures and events

No Comments

No Known Activations