INDEX

Explanations

phrases that emphasize totality or completeness

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.01

2:0.07

3:0.06

4:0.26

5:0.03

6:0.25

7:0.09

8:0.03

9:0.03

10:0.04

11:0.05

Negative Logits

 accurately

-1.57

®

-1.41

 underest

-1.39

 attributed

-1.35

 describing

-1.31

 underestimate

-1.31

ori

-1.31

rification

-1.30

 contained

-1.29

 exhibited

-1.28

POSITIVE LOGITS

 realms

1.78

stanbul

1.70

abad

1.63

perate

1.60

 stages

1.55

 Balkans

1.52

outheastern

1.52

 depths

1.52

gro

1.46

Balt

1.45

Activations Density 0.000%

phrases that emphasize totality or completeness

No Comments

No Known Activations