INDEX

Explanations

the verb "to be."

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

0:0.03

1:0.03

2:0.29

3:0.10

4:0.09

5:0.03

6:0.06

7:0.08

8:0.07

9:0.04

10:0.07

11:0.07

Negative Logits

 wrongly

-1.53

��

-1.48

 thumb

-1.43

 Furious

-1.43

sych

-1.43

ulp

-1.42

 wrongful

-1.40

�

-1.39

 Winged

-1.37

ank

-1.32

POSITIVE LOGITS

real

1.88

Palest

1.82

Econom

1.58

Reviewed

1.56

define

1.55

TPPStreamerBot

1.52

DragonMagazine

1.51

utical

1.49

rss

1.44

Palestinian

1.43

Activations Density 0.000%

the verb "to be."

No Comments

No Known Activations