INDEX

Explanations

references to Hitler, specifically in a comparative context

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

0:0.05

1:0.05

2:0.16

3:0.08

4:0.12

5:0.06

6:0.05

7:0.05

8:0.11

9:0.07

10:0.08

11:0.08

Negative Logits

jri

-1.64

 Offensive

-1.63

 Conspiracy

-1.52

 POLIT

-1.47

 rocked

-1.45

 Alam

-1.40

lis

-1.39

 Consortium

-1.37

Pix

-1.36

 Solid

-1.35

POSITIVE LOGITS

vernight

1.79

places

1.68

Introduced

1.64

prints

1.57

elsh

1.50

bars

1.49

rely

1.46

meter

1.45

gencies

1.41

valued

1.41

Activations Density 0.000%

references to Hitler, specifically in a comparative context

No Comments

No Known Activations