INDEX

Explanations

phrases indicating claims, decisions, or assertions regarding political actions or accountability

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.02

2:0.11

3:0.08

4:0.13

5:0.05

6:0.05

7:0.05

8:0.08

9:0.08

10:0.13

11:0.13

Negative Logits

#$

-1.43

(&

-1.37

 Bastard

-1.33

verages

-1.32

sbm

-1.30

 Bundy

-1.27

 Belief

-1.24

Awesome

-1.24

Break

-1.23

CLASS

-1.22

POSITIVE LOGITS

).[

1.30

 boutique

1.25

 hers

1.24

 later

1.23

ordable

1.22

 respectively

1.19

 domestically

1.19

 creditor

1.16

".[

1.15

ourt

1.15

Activations Density 0.017%

phrases indicating claims, decisions, or assertions regarding political actions or accountability

No Comments

No Known Activations