INDEX

Explanations

adjectives and phrases indicating approval or condition

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.07

1:0.06

2:0.08

3:0.09

4:0.09

5:0.07

6:0.07

7:0.08

8:0.09

9:0.10

10:0.08

11:0.07

Negative Logits

 substituted

-2.52

 copied

-2.39

 Referred

-2.35

 replaced

-2.26

 reproduced

-2.26

 flashed

-2.23

 relied

-2.20

 resultant

-2.20

 pronounce

-2.19

produced

-2.17

POSITIVE LOGITS

 Emir

2.45

 Undead

2.44

 Seym

2.40

 Athen

2.34

lehem

2.31

 Berm

2.27

 Erit

2.25

 Indones

2.25

 Yemen

2.24

 Yemeni

2.21

Activations Density 0.000%

adjectives and phrases indicating approval or condition

No Comments

No Known Activations