INDEX

Explanations

rights, authority, and positions of power

oai_token-act-pair · gpt-3.5-turbo

expressions of rights and authority

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

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

irie

-0.65

 Hort

-0.63

rome

-0.60

zyme

-0.57

UFF

-0.56

 Spray

-0.55

unct

-0.55

 aloud

-0.53

 Features

-0.53

aming

-0.52

POSITIVE LOGITS

to

1.20

to

0.91

 thereto

0.90

To

0.79

To

0.74

TO

0.70

eto

0.67

 decide

0.65

thumbnails

0.64

lig

0.62

Activations Density 0.141%

rights, authority, and positions of power

expressions of rights and authority

No Comments

No Known Activations