INDEX

Explanations

instances of equality and collective awareness

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

1:0.35

2:0.06

3:0.05

4:0.08

5:0.05

6:0.07

7:0.08

8:0.03

9:0.07

10:0.04

11:0.03

Negative Logits

shown

-3.30

displayText

-3.15

enance

-3.10

avez

-2.91

rather

-2.71

olved

-2.70

 wherein

-2.56

areth

-2.51

ISON

-2.50

ort

-2.49

POSITIVE LOGITS

 everybody

6.84

 Everybody

6.00

Everybody

5.86

 everyone

5.81

 nobody

5.63

everyone

5.61

Everyone

5.58

 Everyone

5.58

Nobody

5.26

 Nobody

5.23

Activations Density 0.052%

instances of equality and collective awareness

No Comments

No Known Activations