INDEX

Explanations

instances of the word "made" and phrases that indicate causation or outcomes

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

2:0.14

3:0.08

4:0.07

5:0.04

6:0.06

7:0.16

8:0.04

9:0.06

10:0.13

11:0.11

Negative Logits

 Dwight

-1.59

uilt

-1.59

 Tacoma

-1.50

 Pengu

-1.47

 Loch

-1.40

 Doodle

-1.37

furt

-1.33

Buc

-1.32

FY

-1.30

dump

-1.30

POSITIVE LOGITS

Attempts

1.49

Reviewed

1.47

 proxy

1.41

 proxies

1.41

 masked

1.39

 detector

1.38

 censorship

1.37

 verify

1.34

istrate

1.33

 intimidation

1.33

Activations Density 0.000%

instances of the word "made" and phrases that indicate causation or outcomes

No Comments

No Known Activations