INDEX

Explanations

phrases that indicate confrontation or conflict

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

0:0.02

1:0.03

2:0.06

3:0.25

4:0.01

5:0.03

6:0.07

7:0.14

8:0.05

9:0.12

10:0.06

11:0.12

Negative Logits

 Helpful

-1.29

stadt

-1.28

enthal

-1.13

nor

-1.09

ERSON

-1.07

hift

-1.06

Requires

-1.05

 projecting

-1.05

donald

-1.05

enhagen

-1.03

POSITIVE LOGITS

 ensued

1.27

 Achilles

1.16

 Atlantis

1.14

emate

1.10

weed

1.09

foe

1.09

 advers

1.08

 Bros

1.08

 Rabbit

1.07

 raged

1.07

Activations Density 0.014%

phrases that indicate confrontation or conflict

No Comments

No Known Activations