INDEX

Explanations

phrases expressing interests, preferences, and ethical concerns

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

0:0.02

1:0.42

2:0.08

3:0.02

4:0.01

5:0.03

6:0.06

7:0.04

8:0.04

9:0.10

10:0.07

11:0.04

Negative Logits

�

-1.62

lio

-1.49

�

-1.48

Library

-1.42

 pione

-1.41

武

-1.39

シャ

-1.37

CHA

-1.33

 Globe

-1.33

ukemia

-1.31

POSITIVE LOGITS

 Governments

1.73

 Poles

1.65

 frogs

1.58

 Bulgar

1.57

sew

1.54

 raining

1.47

 tigers

1.41

 Regulations

1.36

 frog

1.33

 uphill

1.32

Activations Density 0.530%

phrases expressing interests, preferences, and ethical concerns

No Comments

No Known Activations