INDEX

Explanations

emotions related to societal discontent and political critique

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_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.06

1:0.05

2:0.04

3:0.06

4:0.03

5:0.09

6:0.03

7:0.06

8:0.06

9:0.26

10:0.15

11:0.07

Negative Logits

 sidx

-1.33

 simulator

-1.26

 renovated

-1.20

ortium

-1.15

ciplinary

-1.14

ABE

-1.12

idge

-1.11

inances

-1.10

 Tycoon

-1.09

abase

-1.08

POSITIVE LOGITS

 disson

1.36

 engulf

1.35

 abound

1.31

 cynicism

1.29

 perv

1.28

 uttered

1.28

 adversity

1.28

 bigotry

1.18

 outp

1.16

 manifested

1.15

Activations Density 0.519%

emotions related to societal discontent and political critique

No Comments

No Known Activations