INDEX

Explanations

words and phrases indicating locations or settings related to activities and events

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

0:0.03

1:0.03

2:0.21

3:0.05

4:0.02

5:0.02

6:0.11

7:0.09

8:0.16

9:0.06

10:0.09

11:0.07

Negative Logits

thia

-1.27

ع

-1.04

 oneself

-1.01

hematically

-1.00

 Saudis

-0.99

DERR

-0.99

 Mourinho

-0.98

Muslims

-0.98

 Muslims

-0.97

ł

-0.97

POSITIVE LOGITS

 doorstep

1.47

 headquarters

1.40

 counterparts

1.30

 intersection

1.25

 institution

1.23

 behest

1.20

 lair

1.17

 vantage

1.15

 entrance

1.14

 counterpart

1.14

Activations Density 0.022%

words and phrases indicating locations or settings related to activities and events

No Comments

No Known Activations