INDEX

Explanations

references and citations in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.15

1:0.06

2:0.06

3:0.03

4:0.25

5:0.10

6:0.04

7:0.04

8:0.05

9:0.03

10:0.07

11:0.06

Negative Logits

Merit

-1.83

 guiActiveUnfocused

-1.67

arbon

-1.55

eworks

-1.53

irtual

-1.53

rompt

-1.50

 sustainability

-1.45

andowski

-1.43

mone

-1.43

ente

-1.40

POSITIVE LOGITS

 Classification

1.57

argon

1.57

 seiz

1.52

↑

1.48

 Includes

1.46

 Hist

1.41

■

1.38

gam

1.35

utenant

1.35

代

1.35

Activations Density 0.040%

references and citations in a text

No Comments

No Known Activations